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 .
Response to Amendment
A preliminary amendment, filed January 16, 2026 has been entered and made of record. Claim 1 is amended; and claims 2-20 are new. By this amendment, claims 1-20 are currently pending for examination.
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.
Claims 1, 3, 8, 10-11, and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, (US-PGPUB 20170366795)
In regards to claim 1, Chou et al discloses a depth estimation system,
comprising:
a plurality of cameras configured to capture a plurality of source images from a plurality of different viewpoints of a scene, (see at least: Fig. 1, Par. 0034, the first camera 12 and the second camera 14 are respectively configured to capture one of left-eye and right-eye images, [i.e., plurality of cameras, “cameras 12 and 14” configured to capture a plurality of source images, from a plurality of different viewpoints of a scene, “capture one of left-eye and right-eye images implicitly from different viewing angles”]);
at least one memory,
instructions for deriving depth estimates, (see at least: Fig. 1, and Par. 0035, the image processing circuit 16 includes … a depth generating module 162, which generates a depth map, “i.e., the CPU implicitly provides instruction generating the depth map”); and
at least one processor, (Par. 0035, “CPU”) communicatively connected to the at least one memory and the plurality of cameras, (see at least: Par. 0035, the CPU implicitly includes a memory and a processor. Further, from Fig. 1, the image processing circuit 16 is implicitly connected to the plurality of cameras); and configured to execute the instructions to:
extract a set of feature information from the plurality of source images, (see at least: Par. 0039, depth generating module 162 calculates the displacement of each pixel in the first image and the corresponding pixel in the upscaled second image according to the location of each pixel in the first image and the upscaled second image to serve as the disparity, [i.e., extract a set of feature information from the plurality of source images, “displacement of each pixel in the first image and the corresponding pixel in the upscaled second image”]);
determine a set of disparity information between at least two of the plurality of source images using the set of feature information, (see at least: Par. 0039, the depth generating module 162 directly calculates disparity of each pixel in the first image and the corresponding pixel in the upscaled second image, which implicitly using the displacement of each pixel in the first image and the corresponding pixel in the upscaled second image”]); and
derive at least one depth map corresponding to the scene, based on: the set of disparity information; at least one baseline distance measured between corresponding cameras used to capture the at least two of the plurality of source images; and the plurality of source images, (see at least: Figs. 1-2, Par. 0039-0040, the depth generating module 162 generates a depth map with use of the first image and the upscaled second image (step S206), …. the depth generating module 162 … estimates the depth of each pixel according to the focal lengths of the first camera 12 and the second camera 14 taking the first image and the second image, the baseline distance between the first camera 12 and the second camera 14, and the disparity of each pixel, [i.e., derive at least one depth map corresponding to the scene, “generating a depth map corresponding the scene”, based on the set of disparity information, “the disparity of each pixel”; at least one baseline distance measured between corresponding cameras used to capture the at least two of the plurality of source images, “the baseline distance between the first camera 12 and the second camera 14, implicitly used to capture the one of left-eye and right-eye images”; and the plurality of source images, “using of the first image and the upscaled second image”]).
Chou et al does not expressly disclose that at least one memory, is configured to store the plurality of source images.
However, the image processing circuit 16 comprises the CPU, which implicitly comprising memory and processor; which the CPU (memory), obviously stores the left-eye and right-eye images acquired by the cameras 12, and 14, as the CPU is connected to the first camera 12 and the second camera 14, as well as other processed data form different modules of the image processing circuit.
Therefore, Chou is functionally equivalent to the recited limitations of claim 1 as addressed above.
In regards to claim 3, Chou obviously discloses the limitations of claim 1.
Chou further discloses wherein the plurality of cameras is a stereo pair of cameras, (see at least: Par. 0034, the first camera 12 and the second camera 14 are respectively configured to capture one of left-eye and right-eye images required for generating a stereo image, [i.e., the plurality of cameras, (12, 14), is a stereo pair of cameras, “implicit by generating a stereo image”]).
In regards to claim 8, Chou obviously discloses the limitations of claim 1.
Chou further discloses wherein determining the set of disparity information comprises calibrating the plurality of source images using at least one of unskewing, sharpening, perspective adjustment, adjusting faulty pixels, or noise reduction, (Chou, see at least: Par. 0050, the first image processing module 467 and the second image processing module 468 may further adjust the brightness, the contrast, the color temperature, the white balance, the sharpness, or the vividness of the images or remove noise, [i.e., calibrating the plurality of source images using at least one of unskewing, sharpening, perspective adjustment, adjusting faulty pixels, or noise reduction, ““implicit by adjusting the sharpness or removing noise for the first and second images”]).
Regarding claim 10, claim 10 recites substantially similar limitations as set forth in claim 1. As such, claim 10 is rejected for at least similar rational.
The Examiner further acknowledged the following additional limitation(s): “a method for depth estimation”. However, Chou discloses the “method for depth estimation”, (see at least: Par. 0006, a stereo image generating method … and a depth map is generated, “i.e., method for depth estimation”).
Regarding claim 11, claim 11 recites substantially similar limitations as set forth in claim 3. As such, claim 11 is rejected for at least similar rational.
Regarding claim 17, claim 17 recites substantially similar limitations as set forth in claim 1. As such, claim 17 is rejected for at least similar rational.
The Examiner further acknowledged the following additional limitation(s): “a non-transitory computer-readable medium executable by at least one processor to perform a method for depth estimation”. However, Chou discloses the “non-transitory computer-readable medium executable by at least one processor to perform a method for depth estimation”, (see at least: Par. 0035, each module in the image processing circuit 16 is, for instance, computer programs stored in the storage apparatus. These programs may be loaded by the processor to execute the stereo image generating method, [i.e., non-transitory computer-readable medium executable by at least one processor to perform a method for depth estimation, “computer programs stored in the storage apparatus may be loaded by the processor to execute the stereo image generating method”]).
Regarding claim 18, claim 18 recites substantially similar limitations as set forth in claim 3. As such, claim 18 is rejected for at least similar rational.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, (US-PGPUB 20170366795) in view of Taimouri et al, (US-Patent 10,466,714)
Chou obviously discloses the limitations of claim 1.
Chou does not expressly disclose wherein the at least one processor is further configured to depict a visualization representing the at least one depth map on the display.
However, Taimouri discloses wherein the at least one processor is further configured to depict a visualization representing the at least one depth map on the display, (see at least: col. 5, lines 7-11, and col. 8, lines 26-27, at step 812 computing device 115 can display the estimated depth maps 726 on a display 117).
Chou and Taimouri are combinable because they are both concerned with stereo images-based depth map generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify Chou, to use the a display 117, as though by Taimouri, in order to display the estimated depth maps 726 on a display 117, (Taimouri, col. 8, lines 26-27).
Claims 4, 12, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, (US-PGPUB 20170366795) in view of Fine et al, (US-PGPUB 20190012818)
In regards to claim 4, Chou obviously discloses the limitations of claim 1.
Chou does not expressly disclose wherein the at least one processor is further configured to execute the instructions to modify at least one of the plurality of source images based on the at least one depth map.
However, Fine discloses modify at least one of the plurality of source images based on the at least one depth map, (see at least: Par. 0005, capturing an image(s) by each camera, mapping regions of the image(s) to the depth map(s), and adjusting the image(s) according to the corresponding depth map(s), [i.e., modifying at least one of the plurality of source images, “adjusting the images captured by each camera”, based on the at least one depth map, “according to the corresponding depth maps”]).
Chou and Fine are combinable because they are both concerned with depth map generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify Chou, to map regions of the image(s) to the depth map(s), and adjusting the image(s) according to the corresponding depth map(s), as though by Fine, in order to combine digital images having a parallax shift into a panoramic image, (Fine, Par. 0041)
Regarding claim 12, claim 12 recites substantially similar limitations as set forth in claim 4. As such, claim 12 is rejected for at least similar rational.
Regarding claim 19, claim 19 recites substantially similar limitations as set forth in claim 4. As such, claim 19 is rejected for at least similar rational.
Claims 5 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, (US-PGPUB 20170366795) in view of Criminisi, (US-PGPUB 20150248765)
In regards to claim 5, Chou obviously discloses the limitations of claim 1.
Chou does not expressly disclose wherein the plurality of source images comprises RGB images.
However, Criminisi discloses wherein the plurality of source images comprises RGB images, (see at least: Fig. 1, Par. 0024, the system 100 may combine or use information from multiple RGB images to generate a single depth map, “i.e., plurality of source images comprises RGB images”]).
Chou and Criminisi are combinable because they are both concerned with depth map generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify Chou, by substituting the Chou’s first camera 12 and second camera 14, with RGB cameras, in order to generate depth map based on multiple RGB images, (Criminisi, Par. 0024).
Regarding claim 13, claim 13 recites substantially similar limitations as set forth in claim 5. As such, claim 13 is rejected for at least similar rational.
Claims 6 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, (US-PGPUB 20170366795) in view of Abbott, (US-PGPUB 20140368506)
In regards to claim 6, Chou obviously discloses the limitations of claim 1.
Chou does not expressly disclose wherein determining the set of disparity information comprises iteratively refining the set of disparity information.
Abbott discloses wherein determining the set of disparity information comprises iteratively refining the set of disparity information, (see at least: Par. 0036, Iteratively refining 620 may include iteratively refining the disparity plane estimates, [i.e., iteratively refining the set of disparity information, “disparity plane estimates”]).
Chou and Abbott are combinable because they are both concerned with disparity information generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify Chou, to use the Iteratively refining 620, as though by Abbott, in order to the disparity plane estimation module 244, as though by Abbott, in order to iteratively refining the disparity plane estimates, (Abbott, Par. 0036).
Regarding claim 14, claim 14 recites substantially similar limitations as set forth in claim 6. As such, claim 14 is rejected for at least similar rational.
Claims 7, 15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, and Abbott, as applied to claim 6 above; and further in view of Pang et al, (“Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching”, 2017 IEEE International Conference on Computer Vision Workshops, October 22-29, 2017, PP 878-886)
In regards to claim 7, the combine teaching Chou and Abbott as whole discloses the limitations of claim 6.
The combine teaching Chou and Abbott as whole does not expressly disclose wherein iteratively refining the set of disparity information is performed using a convolutional neural network (CNN).
However, Pang discloses iteratively refining the set of disparity information is performed using a convolutional neural network (CNN), (see at least: Page 879, section 3.1, “e.g., denoising and de blurring, can be improved with post-facto iterative refinement”; and section 3.2, right-hand-column, where the eq. (2), represents the refined set of disparity information in the second stage of the two-stage CNN. Our network explicitly supervises the residual signals, leading to effective disparity refinement, [i.e., iteratively refining the set of disparity information, “post-facto iterative refinement”, is performed using a convolutional neural network (CNN), “using second stage of the CNN”]).
Chou, Abbott, and Pang are combinable because they are all concerned with disparity information generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify the combine teaching Chou and Abbott, to use the two-stage CNN, as though by Pang, in order to explicitly supervise the residual signals, leading to effective disparity refinement, (Page 880, right-hand-column, 1st paragraph).
Regarding claim 15, claim 15 recites substantially similar limitations as set forth in claim 7. As such, claim 15 is rejected for at least similar rational.
Regarding claim 20, claim 20 recites substantially similar limitations as set forth in claim 7. As such, claim 20 is rejected for at least similar rational.
Claims 9 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Chou et al, (US-PGPUB 20170366795) in view of Wang et al, (“Generative Adversarial Networks for Parallel Vision”, 20-22 October 2017, IEEE, PP 7070-7075); and further in view of Navab, (US-PGPUB 20030146922)
In regards to claim 9, Chou obviously discloses the limitations of claim 1.
Chou does not expressly disclose wherein determining the set of disparity information comprises: generating at least one virtual target image from the plurality of source images using a generative model, wherein the at least one virtual target image depicts at least one of the plurality of different viewpoints; and comparing the at least one virtual target image with a subset of the plurality of source images that shares the at least one of the plurality of different viewpoints.
Wang et al discloses generating at least one virtual target image from the plurality of source images using a generative model, (see at least: Abstract, Generative Adversarial Networks (GANs) can generate more realistic images for parallel vision research; and Page 7071, We use the computer animation-like techniques to model the artificial scenes. Large-scale virtual images and their annotation information as shown in the following figure, including semantic/instance segmentation, object bounding box, object tracking, optical flow, and depth; and from section III, Figs. 6-7, generator and a discriminator make up the whole model, [i.e., generating at least one virtual target image from the plurality of source images, “implicit by generating more realistic images of at least one view”, using a generative model, “GAN”]).
Chou and Wang are combinable because they are both concerned with disparity information generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify Chou, to use GAN model, where the generator and a discriminator make up the whole model, as though by Wang, in order to generate more realistic virtual pedestrians in a specific scene, (Figs. 6-7).
The combine teaching Chou and Wang as whole does not expressly disclose comparing the at least one virtual target image with a subset of the plurality of source images that shares the at least one of the plurality of different viewpoints.
Navab discloses comparing the at least one virtual target image with a subset of the plurality of source images that shares the at least one of the plurality of different viewpoints, (see at least: Par. 0012, determining a homography between the virtual image and the source image for each source image, and determining a correlation for each virtual image among the plurality of source images, [i.e., comparing the at least one virtual target image with a subset of the plurality of source images, “determining a correlation for each virtual image among the plurality of source images”, that shares the at least one of the plurality of different viewpoints, “i.e., implicit by determining the homography between the virtual image and the source image for each source image”]).
Chou, Wang, and Navab are combinable because they are all concerned with disparity information generation. Therefore, it would have been obvious to a person of ordinary skill in the art, to modify the combine teaching Chou and Wang, to determine the correlation for each virtual image among the plurality of source images, as though by Navab, in order to remove an object in an image, (Navab, Par. 0008)
Regarding claim 16, claim 16 recites substantially similar limitations as set forth in claim 9. As such, claim 16 is rejected for at least similar rational.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMARA ABDI whose telephone number is (571)272-0273. The examiner can normally be reached 9:00am-5:30pm.
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, Vu Le can be reached at (571) 272-7332. 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.
/AMARA ABDI/Primary Examiner, Art Unit 2668 06/04/2026
Prosecution Insights