DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 18 and 20 are objected to because of the following informalities:
For claim 18, Examiner believes this claim should be amended in the following manner:
A system comprising:
at least one processor; and
a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, by the at least one processor, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
For claim 20, Examiner believes this claim should be amended in the following manner:
A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving, by the at least one processor, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
Appropriate correction is required.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP §§ 706.02(l)(1) - 706.02(l)(3) for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/process/file/efs/guidance/eTD-info-I.jsp.
Claims 1, 5, 7, 13-16, 18 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 5, 7, 13-16, 18 and 20 of U.S. Patent 11,880,947. Claims 2, 3, 6 and 8-12 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 2, 3, 6 and 8-12 of U.S. Patent 11,880,947 in view of Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021 (made of record of the IDS submitted 1/06/2025).
The following is a claim comparison of claims 1-18 and 20 of the instant application and claims 1-3, 5-16, 18 and 20 of U.S. Patent 11,880,947.
Application No. 19/010,631
U.S. Patent 11,880,947
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first upper-body garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second upper-body garment in a second pose;
modifying the second pose of the second person depicted in the second video to match the first pose of the first person depicted in the first video; extracting appearance data associated with the second person from the second video; extracting motion data associated with the first person from the first video; and
generating a third video that includes a depiction of the second person having the appearance data associated with the second person and the motion data of the first person replacing the first upper-body garment worn by the first person in the first video with the second upper-body garment based on the third video.
2
2
3
3
4
1
5
5
6
6
7
7
8
8
9
12
10
9
11
10
12
11
13
13
14
14
15
15
16
16
17
1
18. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
18. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving a first video that includes a depiction of a first person wearing a first upper-body garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second upper-body garment in a second pose;
modifying the second pose of the second person depicted in the second video to match the first pose of the first person depicted in the first video; extracting appearance data associated with the second person from the second video; extracting motion data associated with the first person from the first video; and
generating a third video that includes a depiction of the second person having the appearance data associated with the second person and the motion data of the first person replacing the first upper-body garment worn by the first person in the first video with the second upper-body garment based on the third video.
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising: receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform operations comprising: receiving a first video that includes a depiction of a first person wearing a first upper-body garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second upper-body garment in a second pose;
modifying the second pose of the second person depicted in the second video to match the first pose of the first person depicted in the first video; extracting appearance data associated with the second person from the second video; extracting motion data associated with the first person from the first video; and
generating a third video that includes a depiction of the second person having the appearance data associated with the second person and the motion data of the first person replacing the first upper-body garment worn by the first person in the first video with the second upper-body garment based on the third video.
Claims 1, 5, 7, 13-16, 18 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 5, 7, 13-16, 18 and 20 of U.S. Patent 11,880,947. Claims 2, 3, 6 and 8-12 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 2, 3, 6 and 8-12 of U.S. Patent 11,880,947 in view of Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021 (made of record of the IDS submitted 1/06/2025).
For independent claim 1, claim 1 of U.S. Patent 11,880,947 anticipates the limitations of claim 1 as shown in the claim chart above. Therefore, claim 1 is not patentably distinct from claim 1 of U.S. Patent 11,880,947.
For dependent claims 5, 7 and 13-16, claims 5, 7, 13-16 of U.S. Patent 11,880,947 mirror and recite the same limitations of claims 5, 7 and 13-16 as set forth in the claim chart above. Therefore, claims 5, 7 and 13-16 are not patentably distinct from claims 5, 7 and 13-16 of U.S. Patent 11,880,947.
For independent claim 18, claim 18 of U.S. Patent 11,880,947 anticipates the limitations of claim 18 as shown in the claim chart above. Therefore, claim 18 is not patentably distinct from claim 18 of U.S. Patent 11,880,947.
For independent claim 20, claim 20 of U.S. Patent 11,880,947 anticipates the limitations of claim 20 as shown in the claim chart above. Therefore, claim 20 is not patentably distinct from claim 20 of U.S. Patent 11,880,947.
For dependent claims 2, 3, 6 and 8-12, claims 2, 3, 6 and 8-12 of U.S. Patent 11,880,947 do not disclose a whole body/full body segmentation. However, these limitations are well-known in the art as disclosed in Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021. It would been obvious to apply the use of a whole body/full body segmentation to facilitate a whole body/full body outfit transfer from a first person to a second person for appropriate garment transfer (page 7502/Fig. 2 and page 7503/Fig. 3) as disclosed in Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021. Claims 2, 3, 6 and 8-12 of U.S. Patent 11,880,947 otherwise recite the same limitations of claims 2, 3, 6 and 8-12 of the instant application. Therefore, claims 2, 3, 6 and 8-12 are not patentably distinct from claims 2, 3, 6 and 8-12 of U.S. Patent 11,880,947.
Claims 1, 4, 6-8 and 13-16 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-4 and 12-16 of U.S. Patent 12,198,398. Claims 18 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1 and 2 of U.S. Patent 12,198,398 in view of Wu et al. (WO 2021/197143 A1).
The following is a claim comparison of claims 1, 4, 6-8, 13-16, 18 and 20 of the instant application and claims 1-4 and 12-16 of U.S. Patent 12,198,398.
Application No. 19/010,631
U.S. Patent 12,198,398
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first real-world object; extracting, by a first machine learning technique, appearance data representing an appearance of the first real-world object from the first video;
obtaining a second video that includes a depiction of a second real-world object; extracting, by the first machine learning technique, motion data representing motion of the second real-world object from the second video; applying the motion data representing the motion of the second real-world object extracted from the second video to the appearance of the first real-world object extracted from the first video; and
generating, by a second machine learning technique, a third video that includes a depiction of the first real-world object based on the appearance data representing the appearance of the first real-world object and the motion data representing the motion of the second real-world object, the first and second machine learning techniques trained by: accessing a pair of training images comprising a first training image, depicting a given object wearing a particular garment and performing a first pose, and a second training image depicting the same given object wearing the same particular garment and performing a second pose; processing, by the first machine learning technique, the first training image and the second training image to extract features from the first training image and pose features from the second training image; processing, by the second machine learning technique, the features extracted from the first training image and the pose features extracted from the second training image to estimate a new image depicting the given object performing the second pose wearing the particular garment; and computing a deviation between the new image estimated by the second machine learning technique and the second training image to update one or more parameters of the first or second machine learning techniques.
2. The method of claim 1, wherein the first real-world object comprises a first person and the second real-world object comprises a second person.
4
1
6
3
7
1 and 4
8
12
13
13
14
14
15
15
16
16
18. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first real-world object; extracting, by a first machine learning technique, appearance data representing an appearance of the first real-world object from the first video;
obtaining a second video that includes a depiction of a second real-world object; extracting, by the first machine learning technique, motion data representing motion of the second real-world object from the second video; applying the motion data representing the motion of the second real-world object extracted from the second video to the appearance of the first real-world object extracted from the first video; and
generating, by a second machine learning technique, a third video that includes a depiction of the first real-world object based on the appearance data representing the appearance of the first real-world object and the motion data representing the motion of the second real-world object, the first and second machine learning techniques trained by: accessing a pair of training images comprising a first training image, depicting a given object wearing a particular garment and performing a first pose, and a second training image depicting the same given object wearing the same particular garment and performing a second pose; processing, by the first machine learning technique, the first training image and the second training image to extract features from the first training image and pose features from the second training image; processing, by the second machine learning technique, the features extracted from the first training image and the pose features extracted from the second training image to estimate a new image depicting the given object performing the second pose wearing the particular garment; and computing a deviation between the new image estimated by the second machine learning technique and the second training image to update one or more parameters of the first or second machine learning techniques.
2. The method of claim 1, wherein the first real-world object comprises a first person and the second real-world object comprises a second person.
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first real-world object; extracting, by a first machine learning technique, appearance data representing an appearance of the first real-world object from the first video;
obtaining a second video that includes a depiction of a second real-world object; extracting, by the first machine learning technique, motion data representing motion of the second real-world object from the second video; applying the motion data representing the motion of the second real-world object extracted from the second video to the appearance of the first real-world object extracted from the first video; and
generating, by a second machine learning technique, a third video that includes a depiction of the first real-world object based on the appearance data representing the appearance of the first real-world object and the motion data representing the motion of the second real-world object, the first and second machine learning techniques trained by: accessing a pair of training images comprising a first training image, depicting a given object wearing a particular garment and performing a first pose, and a second training image depicting the same given object wearing the same particular garment and performing a second pose; processing, by the first machine learning technique, the first training image and the second training image to extract features from the first training image and pose features from the second training image; processing, by the second machine learning technique, the features extracted from the first training image and the pose features extracted from the second training image to estimate a new image depicting the given object performing the second pose wearing the particular garment; and computing a deviation between the new image estimated by the second machine learning technique and the second training image to update one or more parameters of the first or second machine learning techniques.
2. The method of claim 1, wherein the first real-world object comprises a first person and the second real-world object comprises a second person.
Claims 1, 4, 6-8 and 13-16 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-4 and 12-16 of U.S. Patent 12,198,398. Claims 18 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1 and 2 of U.S. Patent 12,198,398 in view of Wu et al. (WO 2021/197143 A1).
For independent claim 1, claims 1 and 2 of U.S. Patent 12,198,398 anticipates the limitations of claim 1 as shown in the claim chart above. Therefore, claim 1 is not patentably distinct from claims 1 and 2 of U.S. Patent 12,198,398.
For dependent claims 4, 6-8 and 13-16, claims 1, 3-4 and 12-16 of U.S. Patent 12,198,398 mirror and recite the same limitations of claims 4, 6-8 and 13-16 as set forth in the claim chart above. Therefore, claims 4, 6-8 and 13-16 are not patentably distinct from claims 1, 3-4 and 12-16 of U.S. Patent 12,198,398.
For independent claim 18, claims 1 and 2 of U.S. Patent 12,198,398 do not disclose a system including a memory component having instructions. However, these limitations are well-known in the art as disclosed in Wu et al. (WO 2021/197143 A1). It would have been obvious to apply to use of a system including a processor and a memory storing instructions for execution by the processor to perform the functions of the system to appropriately perform motion transfer (page 7) as taught in Wu et al. (WO 2021/197143 A1). Claims 1 and 2 of U.S. Patent 12,198,398 otherwise discloses the limitations of claim 18 as shown in the claim chart above. Therefore, claim 18 is not patentably distinct from claims 1 and 2 of U.S. Patent 12,198,398.
For independent claim 20, claims 1 and 2 of U.S. Patent 12,198,398 do not disclose a non-transitory computer-readable storage medium having stored thereon instructions. However, these limitations are well-known in the art as disclosed in Wu et al. (WO 2021/197143 A1). It would have been obvious to apply to use of a system including a processor and a memory storing instructions for execution by the processor to perform the functions of the system to appropriately perform motion transfer (page 7) as taught in Wu et al. (WO 2021/197143 A1). Claims 1 and 2 of U.S. Patent 12,198,398 otherwise discloses the limitations of claim 20 as shown in the claim chart above. Therefore, claim 20 is not patentably distinct from claims 1 and 2 of U.S. Patent 12,198,398.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-18 and 20 of U.S. Patent 12,223,672.
The following is a claim comparison of claims 1-20 of the instant application and claims 1-18 and 20 of U.S. Patent 12,223,672.
Application No. 19/010,631
U.S. Patent 12,223,672
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose;
modifying the second pose of the second person depicted in the second video to match the first pose of the first person depicted in the first video by generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person; after modifying the second pose of the second person to match the first pose of the first person, generating a whole-body segmentation of the second garment which the second person is wearing in the third video; and changing appearance data representing an appearance of the first person from wearing the first garment to wearing the second garment based on the whole-body segmentation of the second garment which the second person is wearing.
2
2
3
3
4
11
5
12
6
4
7
5
8
6
9
7
10
8
11
9
12
10
13
13
14
14
15
15
16
16
17
1
18. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
17. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose;
modifying the second pose of the second person depicted in the second video to match the first pose of the first person depicted in the first video by generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person; after modifying the second pose of the second person to match the first pose of the first person, generating a whole-body segmentation of the second garment which the second person is wearing in the third video; and changing appearance data representing an appearance of the first person from wearing the first garment to wearing the second garment based on the whole-body segmentation of the second garment which the second person is wearing.
19
18
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose;
modifying the second pose of the second person depicted in the second video to match the first pose of the first person depicted in the first video by generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person; after modifying the second pose of the second person to match the first pose of the first person, generating a whole-body segmentation of the second garment which the second person is wearing in the third video; and changing appearance data representing an appearance of the first person from wearing the first garment to wearing the second garment based on the whole-body segmentation of the second garment which the second person is wearing.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-18 and 20 of U.S. Patent 12,223,672.
For independent claim 1, claim 1 of U.S. Patent 12,223,672 anticipates the limitations of claim 1 as shown in the claim chart above. Therefore, claim 1 is not patentably distinct from claim 1 of U.S. Patent 12,223,672.
For dependent claims 2-17, claims 1-16 of U.S. Patent 12,223,672 mirror and recite the same limitations of claims 2-17 as set forth in the claim chart above. Therefore, claims 2-17 are not patentably distinct from claims 1-16 of U.S. Patent 12,223,672.
For independent claim 18, claim 17 of U.S. Patent 12,223,672 anticipates the limitations of claim 18 as shown in the claim chart above. Therefore, claim 18 is not patentably distinct from claim 17 of U.S. Patent 12,223,672.
For dependent claim 19, claim 18 of U.S. Patent 12,223,672 mirrors and recites the same limitations of claim 19 as set forth in the claim chart above. Therefore, claim 19 is not patentably distinct from claim 18 of U.S. Patent 12,223,672.
For independent claim 20, claim 20 of U.S. Patent 12,223,672 anticipates the limitations of claim 20 as shown in the claim chart above. Therefore, claim 20 is not patentably distinct from claim 20 of U.S. Patent 12,223,672.
Claims 1, 4, 5, 7, 13-16, 18 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 2, 5-7, 13-16, 18 and 20 of U.S. Patent 12,646,268. Claims 2, 3 and 8-12 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 2-4 and 8-12 of U.S. Patent 12,646,268 in view of Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021 (made of record of the IDS submitted 1/06/2025).
The following is a claim comparison of claims 1-5, 7-16, 18 and 20 of the instant application and claims 1-16, 18 and 20 of U.S. Patent 12,646,268.
Application No. 19/010,631
U.S. Patent 12,646,268
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
1. A method comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose;
obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose;
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data of the first person; and
replacing a depiction of the first garment worn by the first person in the first video with the second garment based on the third video.
2
2 and 3
3
4
4
2
5
2, 5, 6
7
7
8
8
9
12
10
9
11
10
12
11
13
13
14
14
15
15
16
16
18. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
18. A system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose;
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data of the first person; and replacing a depiction of the first garment worn by the first person in the first video with the second garment based on the third video.
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving, by one or more processors, a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose; and
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person.
20. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving a first video that includes a depiction of a first person wearing a first garment in a first pose; obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose;
generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data of the first person; and replacing a depiction of the first garment worn by the first person in the first video with the second garment based on the third video.
Claims 1, 4, 5, 7, 13-16, 18 and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 2, 5-7, 13-16, 18 and 20 of U.S. Patent 12,646,268. Claims 2, 3 and 8-12 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 2-4 and 8-12 of U.S. Patent 12,646,268 in view of Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021 (made of record of the IDS submitted 1/06/2025).
For independent claim 1, claim 1 of U.S. Patent 12,646,268 anticipates the limitations of claim 1 as shown in the claim chart above. Therefore, claim 1 is not patentably distinct from claim 1 of U.S. Patent 12,646,268.
For dependent claims 4, 5, 7 and 13-16, claims 2, 5-7 and 13-16 of U.S. Patent 12,646,268 mirror and recite the same limitations of claims 4, 5, 7 and 13-16 as set forth in the claim chart above. Therefore, claims 4, 5, 7 and 13-16 are not patentably distinct from claims 2, 5-7 and 13-16 of U.S. Patent 12,646,268.
For independent claim 18, claim 18 of U.S. Patent 12,646,268 anticipates the limitations of claim 18 as shown in the claim chart above. Therefore, claim 18 is not patentably distinct from claim 18 of U.S. Patent 12,646,268.
For independent claim 20, claim 20 of U.S. Patent 12,646,268 anticipates the limitations of claim 20 as shown in the claim chart above. Therefore, claim 20 is not patentably distinct from claim 20 of U.S. Patent 12,646,268.
For dependent claims 2, 3 and 8-12, claims 2-4 and 8-12 of U.S. Patent 12,646,268 do not disclose a whole body/full body segmentation. However, these limitations are well-known in the art as disclosed in Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021. It would been obvious to apply the use of a whole body/full body segmentation to facilitate a whole body/full body outfit transfer from a first person to a second person for appropriate garment transfer (page 7502/Fig. 2 and page 7503/Fig. 3) as disclosed in Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021. Claims 2-4 and 8-12 of U.S. Patent 12,646,268 otherwise recite the same limitations of claims 2, 3 and 8-12 of the instant application. Therefore, claims 22, 3 and 8-12 are not patentably distinct from claims 2-4 and 8-12 of U.S. Patent 12,646,268.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 18 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun et al, Human Motion Transfer with 3D Constraints and Detail Enhancement, arXiv, May 2020 (hereinafter “Sun”) in view of Wu et al. (WO 2021/197143 A1, hereinafter “Wu”) (made of record of the IDS submitted 1/06/2025) (citations made with respect to the corresponding English translation enclosed with this Office Action).
For claim 1, Sun discloses a method comprising (page 1): receiving a first video that includes a depiction of a first person wearing a first garment in a first pose (disclosing the method receives two video clips including a first video of depiction of a first person wearing a first garment in a first pose (pages 2-3/Figs. 1-2)); obtaining a second video that includes a depiction of a second person wearing a second garment in a second pose (disclosing the method receives two video clips including a second video of a depiction of a second person wearing a second garment in a second pose (pages 2-3/Figs. 1-2)); and generating a third video that includes a depiction of the second person having appearance data associated with the second person and motion data associated with the first person (disclosing the method generates target frames of a target video as a third video of a depiction of the second person having appearance data of the second person and motion data of the first person to implement motion transfer of first person to the second person (pages 2-3/Figs. 1-2)).
Sun does not specifically disclose one or more processors.
However, these limitations are well-known in the art as disclosed in Wu.
Wu similarly discloses a system and method for receiving first and second videos to perform motion transfer in generating a target video as third video (pages 2-3). Wu explains its system may be implemented with a processor to carry out the functions of its system and method (page 7). It follows Sun may be accordingly modified with the teachings of Wu to implement a processor for performing the functions of its system and method.
A person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention would find it obvious to modify Sun with the teachings of Wu. Wu is analogous art in dealing with a system and method for receiving first and second videos to perform motion transfer in generating a target video as third video (pages 2-3). Wu discloses its use of a processor is advantageous in implementing functions of a system and method to appropriately perform motion transfer (pages 2-3 and 7). Consequently, a PHOSITA would incorporate the teachings of Wu into Sun for implementing functions of a system and method to appropriately perform motion transfer. Therefore, claim 1 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
For claim 18, Sun as modified by Wu discloses a system comprising: at least one processor; and a memory component having instructions stored thereon that, when executed by the at least one processor, cause the at least one processor (Wu discloses a system including a processor and a memory storing instructions for execution by the processor to perform the functions of the system (page 7); and It follows Sun may be accordingly modified with the teachings of Wu to implement a processor and memory for performing the functions of its system and method) to perform operations comprising the method of claim 1 (see above as to claim 1).
For claim 20, Sun as modified by Wu discloses a non-transitory computer-readable storage medium having stored thereon instructions that, when executed by at least one processor, cause the at least one processor (Wu discloses a system including a processor and a memory storing instructions for execution by the processor to perform the functions of the system (page 7); and It follows Sun may be accordingly modified with the teachings of Wu to implement a processor and memory for performing the functions of its system and method) to perform operations comprising the method of claim 1 (see above as to claim 1).
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wu further in view of Liu et al., Spatial-Aware Texture Transformer for High-Fidelity Garment Transfer, IEEE Transactions on Image Processing, vol. 30, August 2021 (hereinafter “Liu ‘1”) (made of record of the IDS submitted 1/06/2025).
For claim 4, depending on claim 1, Sun as modified by Wu discloses extracting the motion data of the first person from the first video (Sun discloses its method extracts motion data of the first person from the first video to implement motion transfer of first person to the second person (pages 2-3/Figs. 1-2)).
Sun as modified by Wu does not specifically disclose extracting appearance data associated with a person.
Liu ‘1 similarly discloses a system and method to perform outfit transfer in augmented reality (page 7499). Liu ‘1 explains its system extracts a garment as appearance data associated with a person from an image of the person (page 7502/Fig. 2). It follows Sun and Wu may be accordingly modified with the teachings of Liu ‘1 to, extract its appearance data associated with its second person from its second video.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Sun and Wu with the teachings of Liu ‘1. Liu ‘1 is analogous art in dealing with a system and method to perform outfit transfer in augmented reality (page 7499). Liu ‘1 discloses its extraction of appearance data is advantageous in generating an appropriate segmentation of a garment to facilitate outfit transfer (page 7502/Fig. 2). Consequently, a PHOSITA would incorporate the teachings of Liu ‘1 into Sun and Wu for generating an appropriate segmentation of a garment to facilitate outfit transfer. Therefore, claim 4 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
Claim(s) 6-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wu further in view of Liu ‘1 further in view of Liu et al., Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 9, May 2021 (hereinafter “Liu ‘2”) (made of record of the IDS submitted 1/06/2025).
For claim 6, depending on claim 1, Sun as modified by Wu and Liu ‘1 discloses
wherein the appearance data associated with the second person comprises a three-dimensional (3D) pose, a full body segmentation, a set of dense keypoints, texture, color, and a garment segmentation (Liu ‘1 similarly discloses a system and method to perform outfit transfer in augmented reality (page 7499); Liu ‘1 explains its system extracts a garment as appearance data associated with a person from an image of the person (page 7502/Fig. 2); Liu ‘1 discloses appearance data associated with a person comprises a 3D pose, a full body segmentation, points associated with a dense pose, texture, color and a garment segmentation (page 7502/Fig. 2 and page 7503/Fig. 3); and it follows Sun and Wu may be accordingly modified with the teachings of Liu ‘1 to implement appearance data for its second person of a three-dimensional (3D) pose, a whole body segmentation, a set of dense points, texture, color, and a garment segmentation to extract its appearance data associated with its second person from its second video to facilitate garment transfer).
Sun as modified by Wu and Liu ‘1 does not specifically disclose keypoints.
However, these limitations are well-known in the art as disclosed in Liu ‘2.
Liu ‘2 similarly discloses a system and method to perform appearance transfer in augmented reality (page 1). Liu ‘2 explains it is known to use keypoints to estimate human body structure to perform human image synthesis and appearance transfer (pages 1 and 2). It follows Sun, Wu and Liu ‘1 may be accordingly modified with the teachings of Liu ‘2 to implement its dense points as dense keypoints to facilitate garment transfer.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Sun, Wu and Liu ‘1 with the teachings of Liu ‘2. Liu ‘2 is analogous art in dealing with a system and method to perform appearance transfer in augmented reality (page 1). Liu ‘2 discloses its use of keypoints is advantageous in estimating human body structure to appropriately perform human image synthesis and appearance transfer (pages 1 and 2). Consequently, a PHOSITA would incorporate the teachings of Liu ‘2 into Sun, Wu and Liu ‘1 for estimating human body structure to appropriately perform human image synthesis and appearance transfer. Therefore, claim 6 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
For claim 7, depending on claim 1, Sun as modified by Wu, Liu ‘1 and Liu ‘2 discloses further comprising extracting appearance data associated with the first person and the motion data associated with the first person by applying a first machine learning technique to the first video and the second video, the first machine learning technique being trained to estimate appearance and motion data associated with an input video (Liu ‘2 similarly discloses a system and method to perform appearance transfer in augmented reality (page 1); Liu ‘2 explains its system implements a generative adversarial network (GAN) as a machine learning technique that is trained to extract appearance data and motion data associated with a person in an input image (pages 5-7/Sections 3.3-3.4); and it follows Sun, Wu and Liu ‘1 may be accordingly modified with the teachings of Liu ‘2 to apply a trained machine learning technique to its first video and its second video to appropriately extract appearance data and motion data associated with its first person and the second person).
For claim 8, depending on claim 7, Sun as modified by Wu, Liu ‘1 and Liu ‘2 discloses wherein the first machine learning technique is trained to generate a three-dimensional (3D) pose of a given real-world object depicted in the input video, a full body segmentation of the given real-world object, a set of dense keypoints of the given real-world object, texture, color, and a garment segmentation of the given real-world object simultaneously (Liu ‘1 similarly discloses a system and method to perform outfit transfer in augmented reality (page 7499); Liu ‘1 discloses a spatial-aware texture generation network as a machine learning technique that is trained to generate a 3D pose of a person as a given real-world object in an input image, a full body segmentation of the person, points associated with a dense pose for the person, texture, color, and a garment segmentation for the person simultaneously (page 7502/Fig. 2, page 7503/Fig. 3 and page 7504); and it follows Sun and Wu may be accordingly modified with the teachings of Liu ‘1 to implement a machine learning technique trained to generate a 3D pose of a given real-world object in its input video, a whole body segmentation of the given real-world object, a set of dense points of the given real-world object, texture, color and a garment segmentation of the given real world object simultaneously; Liu ‘2 similarly discloses a system and method to perform appearance transfer in augmented reality (page 1); Liu ‘2 explains its system implements a generative adversarial network (GAN) as a machine learning technique that is trained to extract appearance data and motion data associated with a person in an input image (pages 5-7/Sections 3.3-3.4); Liu ‘2 explains it is known to use keypoints to estimate human body structure to perform human image synthesis and appearance transfer (pages 1 and 2); and it follows Sun, Wu and Liu ‘1 may be accordingly modified with the teachings of Liu ‘2 to implement its machine learning technique to determine a set of keypoints for a dense pose to appropriately estimate human body structure to facilitate garment transfer).
Claim(s) 13-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wu further in view of Koblin et al. (U.S. Patent Application Publication 2020/0118343 A1, hereinafter “Koblin”) (made of record of the IDS submitted 1/06/2025).
For claim 13, depending on claim 1, Sun as modified by Wu does not disclose using an image capture device of a client device of a first person to capture a first video and a second video.
However, these limitations are well-known in the art as disclosed in Koblin.
Koblin similarly discloses a system and method for presenting augmented reality for display with a client device (page 5/par. 173). Koblin discloses the client device may be equipped with an image capture device as a rear-facing camera and a front-facing camera to simultaneously capture a first video and a second video of users (page 5/par. 174-175; page 6/par. 182 and page 8/par. 236). It follows Sun and Wu may be accordingly modified with the teachings of Koblin to accommodate a client device with an image capture device for capturing its second video of its second person, and, after capturing its second video, capturing its first video of its first person with the image capture device.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Sun and Wu with the teachings of Koblin. Koblin is analogous art in dealing with a system and method for presenting augmented reality for display with a client device (page 5/par. 173). Koblin discloses the use of an image capture device is advantageous in simultaneously capturing first and second videos to appropriately generate new video to present augmented reality (page 5/par. 174-175; page 6/par. 182 and page 8/par. 236). Consequently, a PHOSITA would incorporate the teachings of Koblin into Sun and Wu for simultaneously capturing first and second videos to appropriately generate new video to present augmented reality. Therefore, claim 13 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
For claim 14, depending on claim 13, Sun as modified by Wu and Koblin discloses wherein the second video is captured using a rear-facing camera of the client device and the first video is captured using a front-facing camera of the client device (Koblin similarly discloses a system and method for presenting augmented reality for display with a client device (page 5/par. 173); Koblin discloses the client device may be equipped with an image capture device as a rear-facing camera and a front-facing camera to simultaneously capture a first video and a second video of users (page 5/par. 174-175; page 6/par. 182 and page 8/par. 236); and it follows Sun and Wu may be accordingly modified with the teachings of Koblin to accommodate a client device with an image capture device for capturing its first video and its second video to appropriately present augmented reality).
For claim 15, depending on claim 1, Sun as modified by Wu and Koblin discloses wherein the first video and the second video are captured simultaneously using different cameras of a client device (Koblin similarly discloses a system and method for presenting augmented reality for display with a client device (page 5/par. 173); Koblin discloses the client device may be equipped with an image capture device as a rear-facing camera and a front-facing camera to simultaneously capture a first video and a second video of users (page 5/par. 174-175; page 6/par. 182 and page 8/par. 236); and it follows Sun and Wu may be accordingly modified with the teachings of Koblin to accommodate a client device with an image capture device for capturing its first video and its second video to appropriately present augmented reality).
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun in view of Wu further in view of Jong et al., Short Video Datasets Show Potential for Outfits in Augmented Reality, 2019 International Conference on High Performance Computing and Simulation, July 2019, pages 201-208 (hereinafter “Jong”) (made of record of the IDS submitted 1/06/2025).
For claim 16, depending on claim 1, Sun as modified by Wu does not disclose a particular video depicting change in appearance of a first person is generated in real-time as a first video and a second video are being captured.
However, these limitations are well-known in the art as disclosed in Jong
Jong similarly discloses a system and method to perform outfit transfer in augmented reality (page 201). Jong discloses capturing the first video depicting the first person and the second video depicting the second person (page 203/Fig. 2) and generating a third video depicting the first person wearing the second upper-body garment worn by the second person (pages 204-205/Fig. 5). Jong further explains the outfit transfer may be performed in real-time (page 207).It follows Sun and Wu may be accordingly modified with the teachings of Jong to generate a particular video depicting change in appearance of its first person in real-time as its first video and second video are captured.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Sun and Wu with the teachings of Jong. Jong is analogous art in dealing with a system and method to perform outfit transfer in augmented reality (page 201). Jong discloses the use of video datasets is advantageous in facilitating fully-textured outfit transfer in real-time (page 207). Consequently, a PHOSITA would incorporate the teachings of Jong into Sun and Wu for facilitating fully-textured outfit transfer in real-time. Therefore, claim 16 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
Allowable Subject Matter
Claims 2, 3, 5, 9-12 and 19 would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims, to address any claim objections raised above in the Detailed Action, and upon submission of suitable terminal disclaimers.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLES TSENG whose telephone number is (571)270-3857. The examiner can normally be reached 8-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Xiao Wu can be reached at (571) 272-7761. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CHARLES TSENG/ Primary Examiner, Art Unit 2613
Prosecution Insights