DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Status
2. Claims 1, 15, 19 are currently amended.
3. Claims 1-20 are pending in the present application.
Claim Rejections - 35 USC § 103
4. 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.
5. 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.
6. Claims 1-2, 5, 15 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Chao Shen (US Patent Application Publication No. 2021/0299560 A1) in view of Chuah et al. (US Patent Application Publication No. 2016/0330493 A1) and further in view of Yan et al. (US Patent Application Publication No. 2022/0032189 A1).
7. Regarding Claim 1 (Currently amended), Shen discloses A method, comprising:
generating, from a plurality of images of a target object, a first volume encompassing a first three-dimensional representation of the target object; (see FIG. 2; paragraph [0043] reciting “For example, referring to FIG. 2, an environment interface 210 of the sandbox game includes a capture function control 211. After a user makes a selection on the capture function control 211, a capture interface 220 is displayed, and the capture interface 220 includes an image displayed during image acquisition by using the camera of the terminal, as shown in FIG. 2. The capture interface 220 includes a to-be-acquired object 221. After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud
230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.” A camera is used to capture images of the object 240 from various angles and point cloud 230 is generated as a result. Point cloud 230 together with the infinite virtual volume surrounding it corresponds to a first volume that encompasses the point cloud 230.)
selecting a subspace within the first volume, wherein the subspace is smaller than the first volume and the subspace encompasses the first three-dimensional representation of the target object; (see FIG. 8 wherein a bounding box 820 is selected and place around target object (point cloud 810). The volume generated from the bounding box includes the 3D representation of the object and is a subspace of the first infinite volume.)
generating, from at least a subset of the plurality of images, a second volume, the second volume overlapping the first volume and encompassing a second three-dimensional representation of the target object, (see FIG. 2; paragraph [0043] reciting “For example, referring to FIG. 2, an environment interface 210 of the sandbox game includes a capture function control 211. After a user makes a selection on the capture function control 211, a capture interface 220 is displayed, and the capture interface 220 includes an image displayed during image acquisition by using the camera of the terminal, as shown in FIG. 2. The capture interface 220 includes a to-be-acquired object 221. After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud 230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.”)
generating a cropped volume by cropping the second volume to limit the second volume to the subspace, (see FIG. 8 wherein a bounding box 820 is selected and place around target object (point cloud 810). The volume generated from the bounding box includes the 3D representation of the object and is a subspace of the first infinite volume.)
and rendering a rendered cropped volume based on the cropped volume. (paragraph [0180] reciting “… The GPU is configured to be responsible for rendering and drawing content to be displayed by a display screen. …”)
While not explicitly disclosed by Shen, Chuah discloses generating, from at least a subset of the plurality of images, a second volume, the second volume overlapping the first volume and encompassing a second three-dimensional representation of the target object, (paragraph [0032] reciting “At the beginning of a game session and during game execution when model update is required, high quality and low quality 3D object models are generated at the cloud server. Two sets of low quality 3D object models are generated (with the sets being duplicate of each other) and one set of the low quality 3D object models is sent to the thin client. …” Chuah discloses duplicating 3D object models, thus the point cloud in Shen can be duplicated.)
generating a cropped volume by cropping the second volume to limit the second volume to the subspace, (paragraph [0032] reciting “At the beginning of a game session and during game execution when model update is required, high quality and low quality 3D object models are generated at the cloud server. Two sets of low quality 3D object models are generated (with the sets being duplicate of each other) and one set of the low quality 3D object models is sent to the thin client. …”
Chuah discloses duplicating 3D object models, thus the point cloud in Shen can be duplicated.)
It would have been obvious for a person of ordinary skills in the art before the effective filing date of the claimed invention to modify Shen with Chuah. Chuah discloses duplicating a 3D object so the 3D point cloud in Shen can be duplicated as well. Duplicating the 3D point cloud is beneficial modification since it allows for the user to try different size bounding boxes and other image processes on duplicate versions of the same 3D point cloud.
While the combination of Shen and Chuah does not explicitly disclose, Yan discloses the second volume comprising a plurality of voxels; (paragraph [0038] reciting “A voxel is an abbreviation of a volume pixel, and a 3D object including a voxel may be presented by volumetric rendering or extracting an isosurface of a polygon with a given threshold contour. A voxel is a minimum unit of digital data in 3D space division, and the voxel is usually used for describing a 3D scene in fields such as 3D imaging and scientific data and medical imaging, as well as games.“;
paragraph [0041] reciting “For an ultra-large 3D scene, the scene is voxelized and stored on the magnetic disk. FIG. 3 is a schematic diagram of an example of voxelizing a 3D scene. The 3D scene is divided into a plurality of grids according to an upper surface or a lower surface of a voxel. The size of each grid is the same as the size of the upper surface or the lower surface of the voxel. Each grid represents a position coordinate pair. Objects at each position coordinate pair in the scene are voxelized. As shown in FIG. 3, both a cube A and a cube B at a position coordinate pair (0, 0) represent voxelized objects at the position coordinate pair (0, 0).” Each scene is divided into a grid of voxels. Therefore, the empty space and cartoon character head of Shen is divided into a grid of voxels and a subset of that empty space and cartoon character head also has a plurality of voxels.)
the cropped volume comprising a subset of the plurality of voxels of the second volume; (paragraph [0038] reciting “A voxel is an abbreviation of a volume pixel, and a 3D object including a voxel may be presented by volumetric rendering or extracting an isosurface of a polygon with a given threshold contour. A voxel is a minimum unit of digital data in 3D space division, and the voxel is usually used for describing a 3D scene in fields such as 3D imaging and scientific data and medical imaging, as well as games.“;
paragraph [0041] reciting “For an ultra-large 3D scene, the scene is voxelized and stored on the magnetic disk. FIG. 3 is a schematic diagram of an example of voxelizing a 3D scene. The 3D scene is divided into a plurality of grids according to an upper surface or a lower surface of a voxel. The size of each grid is the same as the size of the upper surface or the lower surface of the voxel. Each grid represents a position coordinate pair. Objects at each position coordinate pair in the scene are voxelized. As shown in FIG. 3, both a cube A and a cube B at a position coordinate pair (0, 0) represent voxelized objects at the position coordinate pair (0, 0).”
Each scene is divided into a grid of voxels. Therefore, the empty space and cartoon character head of Shen is divided into a grid of voxels and a subset of that empty space and cartoon character head also has a subset of the plurality of voxels.)
It would have been obvious for a person of ordinary skills in the art before the effective filing date of the claimed invention to modify Shen and Chuah with Yan. Shen already discloses constructing objects out of voxels and Yan merely discloses that it is possible to have entire 3D virtual scene be divided into voxels through grids.
8. Regarding Claim 2 (Previously presented), Shen further discloses The method of claim 1, wherein the plurality of images are a set of individual images, each image depicting the target object from a particular view angle of a plurality of view angles. (paragraph [0043] reciting “… After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud 230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.”)
9. Regarding Claim 5 (Previously presented), Shen further discloses The method of claim 1, wherein the first volume is a monochrome point cloud or a colored point cloud. (paragraph [0049] reciting “In some implementations, the feature point cloud is used for determining a style of a to-be-constructed target object. The style of the target object may include at least one of a contour, a structure, or color composition of the target object, where the contour of the target object is used for representing the form of appearance of the target object, and the structure of the target object is used for representing a construction structure of the target object, for example, a hollow structure or a solid structure, and the color composition of the target object is used for representing colors of voxel blocks for constructing the target object.“ )
10. Regarding Claim 15 (Currently amended), Shen discloses A non-transitory computer-readable medium storing processor-executable instructions configured to cause one or more processors to: (paragraph [0181] reciting “The memory 1302 may include one or more computer-readable storage media. The computer-readable storage media may be non-transient. The memory 1302 may further include a high-speed random access memory, and a non-volatile memory such as one or more magnetic disk storage devices and a flash memory device. In some embodiments, the non-transient computer-readable storage medium in the memory 1302 is configured to store at least one instruction, and the at least one instruction is used for being executed by the
processor 1301 to implement the virtual-environment-based object construction method provided in the method embodiments of this disclosure.”)
generate, from a plurality of images of a target object, a first volume encompassing a first three-dimensional representation of the target object; (see FIG. 2; paragraph [0043] reciting “For example, referring to FIG. 2, an environment interface 210 of the sandbox game includes a capture function control 211. After a user makes a selection on the capture function control 211, a capture interface 220 is displayed, and the capture interface 220 includes an image displayed during image acquisition by using the camera of the terminal, as shown in FIG. 2. The capture interface 220 includes a to-be-acquired object 221. After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud
230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.” A camera is used to capture images of the object 240 from various angles and point cloud 230 is generated as a result. Point cloud 230 together with the infinite virtual volume surrounding it corresponds to a first volume that encompasses the point cloud 230.)
select a subspace within the first volume, wherein the subspace is smaller than the first volume and the subspace encompasses the first three-dimensional representation of the target object; (see FIG. 8 wherein a bounding box 820 is selected and place around target object (point cloud 810). The volume generated from the bounding box includes the 3D representation of the object and is a subspace of the first infinite volume.)
generate, from at least a subset of the plurality of images, a second volume, the second volume overlapping the first volume and encompassing a second three-dimensional representation of the target object, (see FIG. 2; paragraph [0043] reciting “For example, referring to FIG. 2, an environment interface 210 of the sandbox game includes a capture function control 211. After a user makes a selection on the capture function control 211, a capture interface 220 is displayed, and the capture interface 220 includes an image displayed during image acquisition by using the camera of the terminal, as shown in FIG. 2. The capture interface 220 includes a to-be-acquired object 221. After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud 230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.”)
generate a cropped volume by cropping the second volume to limit the second volume to the subspace, (see FIG. 8 wherein a bounding box 820 is selected and place around target object (point cloud 810). The volume generated from the bounding box includes the 3D representation of the object and is a subspace of the first infinite volume.)
and render a rendered cropped volume based on the cropped volume. (paragraph [0180] reciting “… The GPU is configured to be responsible for rendering and drawing content to be displayed by a display screen. …”)
While not explicitly disclosed by Shen, Chuah discloses generate, from at least a subset of the plurality of images, a second volume, the second volume overlapping the first volume and encompassing a second three-dimensional representation of the target object, (paragraph [0032] reciting “At the beginning of a game session and during game execution when model update is required, high quality and low quality 3D object models are generated at the cloud server. Two sets of low quality 3D object models are generated (with the sets being duplicate of each other) and one set of the low quality 3D object models is sent to the thin client. …” Chuah discloses duplicating 3D object models, thus the point cloud in Shen can be duplicated.)
generate a cropped volume by cropping the second volume to limit the second volume to the subspace, (paragraph [0032] reciting “At the beginning of a game session and during game execution when model update is required, high quality and low quality 3D object models are generated at the cloud server. Two sets of low quality 3D object models are generated (with the sets being duplicate of each other) and one set of the low quality 3D object models is sent to the thin client. …”
Chuah discloses duplicating 3D object models, thus the point cloud in Shen can be duplicated.)
It would have been obvious for a person of ordinary skills in the art before the effective filing date of the claimed invention to modify Shen with Chuah. Chuah discloses duplicating a 3D object so the 3D point cloud in Shen can be duplicated as well. Duplicating the 3D point cloud is beneficial modification since it allows for the user to try different size bounding boxes and other image processes on duplicate versions of the same 3D point cloud.
While the combination of Shen and Chuah does not explicitly disclose, Yan discloses the second volume comprising a plurality of voxels; (paragraph [0038] reciting “A voxel is an abbreviation of a volume pixel, and a 3D object including a voxel may be presented by volumetric rendering or extracting an isosurface of a polygon with a given threshold contour. A voxel is a minimum unit of digital data in 3D space division, and the voxel is usually used for describing a 3D scene in fields such as 3D imaging and scientific data and medical imaging, as well as games.“;
paragraph [0041] reciting “For an ultra-large 3D scene, the scene is voxelized and stored on the magnetic disk. FIG. 3 is a schematic diagram of an example of voxelizing a 3D scene. The 3D scene is divided into a plurality of grids according to an upper surface or a lower surface of a voxel. The size of each grid is the same as the size of the upper surface or the lower surface of the voxel. Each grid represents a position coordinate pair. Objects at each position coordinate pair in the scene are voxelized. As shown in FIG. 3, both a cube A and a cube B at a position coordinate pair (0, 0) represent voxelized objects at the position coordinate pair (0, 0).” Each scene is divided into a grid of voxels. Therefore, the empty space and cartoon character head of Shen is divided into a grid of voxels and a subset of that empty space and cartoon character head also has a plurality of voxels.)
the cropped volume comprising a subset of the plurality of voxels of the second volume; (paragraph [0038] reciting “A voxel is an abbreviation of a volume pixel, and a 3D object including a voxel may be presented by volumetric rendering or extracting an isosurface of a polygon with a given threshold contour. A voxel is a minimum unit of digital data in 3D space division, and the voxel is usually used for describing a 3D scene in fields such as 3D imaging and scientific data and medical imaging, as well as games.“;
paragraph [0041] reciting “For an ultra-large 3D scene, the scene is voxelized and stored on the magnetic disk. FIG. 3 is a schematic diagram of an example of voxelizing a 3D scene. The 3D scene is divided into a plurality of grids according to an upper surface or a lower surface of a voxel. The size of each grid is the same as the size of the upper surface or the lower surface of the voxel. Each grid represents a position coordinate pair. Objects at each position coordinate pair in the scene are voxelized. As shown in FIG. 3, both a cube A and a cube B at a position coordinate pair (0, 0) represent voxelized objects at the position coordinate pair (0, 0).”
Each scene is divided into a grid of voxels. Therefore, the empty space and cartoon character head of Shen is divided into a grid of voxels and a subset of that empty space and cartoon character head also has a subset of the plurality of voxels.)
It would have been obvious for a person of ordinary skills in the art before the effective filing date of the claimed invention to modify Shen and Chuah with Yan. Shen already discloses constructing objects out of voxels and Yan merely discloses that it is possible to have entire 3D virtual scene be divided into voxels through grids.
11. Regarding Claim 19 (Currently amended), Shen discloses A system comprising: one or more non-transitory computer-readable media; and one or more processors communicatively coupled to the one or more non-transitory computer-readable media, the one or more processors configured to execute processor-executable instructions stored in the non-transitory computer-readable media to: (paragraph [0181] reciting “The memory 1302 may include one or more computer-readable storage media. The computer-readable storage media may be non-transient. The memory 1302 may further include a high-speed random access memory, and a non-volatile memory such as one or more magnetic disk storage devices and a flash memory device. In some embodiments, the non-transient computer-readable storage medium in the memory 1302 is configured to store at least one instruction, and the at least one instruction is used for being executed by the
processor 1301 to implement the virtual-environment-based object construction method provided in the method embodiments of this disclosure.”)
generate, from a plurality of images of a target object, a first volume encompassing a first three-dimensional representation of the target object; (see FIG. 2; paragraph [0043] reciting “For example, referring to FIG. 2, an environment interface 210 of the sandbox game includes a capture function control 211. After a user makes a selection on the capture function control 211, a capture interface 220 is displayed, and the capture interface 220 includes an image displayed during image acquisition by using the camera of the terminal, as shown in FIG. 2. The capture interface 220 includes a to-be-acquired object 221. After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud
230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.” A camera is used to capture images of the object 240 from various angles and point cloud 230 is generated as a result. Point cloud 230 together with the infinite virtual volume surrounding it corresponds to a first volume that encompasses the point cloud 230.)
select a subspace within the first volume, wherein the subspace is smaller than the first volume and the subspace encompasses the first three-dimensional representation of the target object; (see FIG. 8 wherein a bounding box 820 is selected and place around target object (point cloud 810). The volume generated from the bounding box includes the 3D representation of the object and is a subspace of the first infinite volume.)
generate, from at least a subset of the plurality of images, a second volume, the second volume overlapping the first volume and encompassing a second three-dimensional representation of the target object, (see FIG. 2; paragraph [0043] reciting “For example, referring to FIG. 2, an environment interface 210 of the sandbox game includes a capture function control 211. After a user makes a selection on the capture function control 211, a capture interface 220 is displayed, and the capture interface 220 includes an image displayed during image acquisition by using the camera of the terminal, as shown in FIG. 2. The capture interface 220 includes a to-be-acquired object 221. After the user long-presses a capture control 222 of the capture interface 220, and holds the terminal to continuously capture around the to-be-acquired object 221, a feature point cloud 230 corresponding to the to-be-acquired object 221 is generated. Then voxel block filling is performed according to the feature point cloud 230 to generate a target object 240, and the target object 240 is displayed according to a display position of the target object 240 in the virtual environment.”)
generate a cropped volume by cropping the second volume to limit the second volume to the subspace, (see FIG. 8 wherein a bounding box 820 is selected and place around target object (point cloud 810). The volume generated from the bounding box includes the 3D representation of the object and is a subspace of the first infinite volume.)
and render a rendered cropped volume based on the cropped volume. (paragraph [0180] reciting “… The GPU is configured to be responsible for rendering and drawing content to be displayed by a display screen. …”)
While not explicitly disclosed by Shen, Chuah discloses generating, from at least a subset of the plurality of images, generate, from at least a subset of the plurality of images, a second volume, the second volume overlapping the first volume and encompassing a second three-dimensional representation of the target object; (paragraph [0032] reciting “At the beginning of a game session and during game execution when model update is required, high quality and low quality 3D object models are generated at the cloud server. Two sets of low quality 3D object models are generated (with the sets being duplicate of each other) and one set of the low quality 3D object models is sent to the thin client. …” Chuah discloses duplicating 3D object models, thus the point cloud in Shen can be duplicated.)
generate a cropped volume by cropping the second volume to limit the second volume to the subspace; and (paragraph [0032] reciting “At the beginning of a game session and during game execution when model update is required, high quality and low quality 3D object models are generated at the cloud server. Two sets of low quality 3D object models are generated (with the sets being duplicate of each other) and one set of the low quality 3D object models is sent to the thin client. …”
Chuah discloses duplicating 3D object models, thus the point cloud in Shen can be duplicated.)
It would have been obvious for a person of ordinary skills in the art before the effective filing date of the claimed invention to modify Shen with Chuah. Chuah discloses duplicating a 3D object so the 3D point cloud in Shen can be duplicated as well. Duplicating the 3D point cloud is beneficial modification since it allows for the user to try different size bounding boxes and other image processes on duplicate versions of the same 3D point cloud.
While the combination of Shen and Chuah does not explicitly disclose, Yan discloses the second volume comprising a plurality of voxels; (paragraph [0038] reciting “A voxel is an abbreviation of a volume pixel, and a 3D object including a voxel may be presented by volumetric rendering or extracting an isosurface of a polygon with a given threshold contour. A voxel is a minimum unit of digital data in 3D space division, and the voxel is usually used for describing a 3D scene in fields such as 3D imaging and scientific data and medical imaging, as well as games.“;
paragraph [0041] reciting “For an ultra-large 3D scene, the scene is voxelized and stored on the magnetic disk. FIG. 3 is a schematic diagram of an example of voxelizing a 3D scene. The 3D scene is divided into a plurality of grids according to an upper surface or a lower surface of a voxel. The size of each grid is the same as the size of the upper surface or the lower surface of the voxel. Each grid represents a position coordinate pair. Objects at each position coordinate pair in the scene are voxelized. As shown in FIG. 3, both a cube A and a cube B at a position coordinate pair (0, 0) represent voxelized objects at the position coordinate pair (0, 0).” Each scene is divided into a grid of voxels. Therefore, the empty space and cartoon character head of Shen is divided into a grid of voxels and a subset of that empty space and cartoon character head also has a plurality of voxels.)
the cropped volume comprising a subset of the plurality of voxels of the second volume; (paragraph [0038] reciting “A voxel is an abbreviation of a volume pixel, and a 3D object including a voxel may be presented by volumetric rendering or extracting an isosurface of a polygon with a given threshold contour. A voxel is a minimum unit of digital data in 3D space division, and the voxel is usually used for describing a 3D scene in fields such as 3D imaging and scientific data and medical imaging, as well as games.“;
paragraph [0041] reciting “For an ultra-large 3D scene, the scene is voxelized and stored on the magnetic disk. FIG. 3 is a schematic diagram of an example of voxelizing a 3D scene. The 3D scene is divided into a plurality of grids according to an upper surface or a lower surface of a voxel. The size of each grid is the same as the size of the upper surface or the lower surface of the voxel. Each grid represents a position coordinate pair. Objects at each position coordinate pair in the scene are voxelized. As shown in FIG. 3, both a cube A and a cube B at a position coordinate pair (0, 0) represent voxelized objects at the position coordinate pair (0, 0).”
Each scene is divided into a grid of voxels. Therefore, the empty space and cartoon character head of Shen is divided into a grid of voxels and a subset of that empty space and cartoon character head also has a subset of the plurality of voxels.)
It would have been obvious for a person of ordinary skills in the art before the effective filing date of the claimed invention to modify Shen and Chuah with Yan. Shen already discloses constructing objects out of voxels and Yan merely discloses that it is possible to have entire 3D virtual scene be divided into voxels through grids.
12. Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Shen in view of Chuah in view of Yan and further in view of Lee et al. (US Patent Application Publication No. 2020/0151963 A1).
13. Regarding Claim 6 (Previously presented), while the combination of Shen, Chuah, and Yan does not explicitly disclose, Lee discloses The method of claim 1, wherein the first volume is generated using an ML model. (paragraph [0019] reciting “Also, an apparatus for generating a training data set for machine learning according to an embodiment of the present invention includes a 3D model extension unit for generating a 3D model for a deformed 3D character based on 3D data pertaining to the 3D character; a 2D image generation unit for generating at least one 2D image corresponding to the generated 3D model; and a training data set generation unit for generating the training data set for machine learning, through which the 3D character is generated from the 2D image, using the 2D image and the 3D model.”)
It would have been obvious to a person of ordinary skills in the before the effective filing date of the claimed invention to modify Shen, Chuah, and Yan with Lee so that the 3D model is generated using ML that has been trained on other 2D images and 3D model data. This is an obviously beneficial modification as machine learning allows the generation of the 3D model from 2D images to be more efficient, quicker, and accurate.
14. Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Shen in view of Chuah in view of Yan and further in view of Eder et al. (US Patent Application Publication No. 2021/0279957 A1)
15. Regarding Claim 7 (Previously presented), while the combination of Shen, Chuah, and Yan does not explicitly disclose, Eder discloses The method of claim 1, wherein the subspace is selected using an ML model. (paragraph [0213] reciting “… In order to account for these challenges this module may include, and/or use a machine learning model (e.g., to interpolate between different images, etc.) to make the map more consistent/complete. Block 3203 is a post processing module for the mapping module similar to and/or the same as other corresponding post processing modules described herein. Once the map (e.g., a 3D model) is created using the spatio-temporal data, geometric filtering algorithms may be applied to this map to create a more consistent/accurate 3D map. Block 3204 illustrates a module comprising a machine learning model which reads the 3D map generated from block 3203 and identifies inventory items associated with that map. The identification here in general is a 3D bounding box around the item of interest. One example scenario is using a model, like a 3D convolutional neural network (CNN), on top of a point cloud that specifies a chair which is occluded by an artificial plant in the scene. The model may comprise a 3D bounding box drawn around a chair (for example), specifying the volume of the chair completely so that the dimensions of the chair can be estimated more accurately. …”)
It would have been obvious to a person of ordinary skills in the before the effective filing date of the claimed invention to modify Shen, Chuah, and Yan with Eder so that a machine learning model is used to generate bounding box around the point cloud 810 of Shen. This is an obviously beneficial modification since it allows the object to be selected without user intervention resulting in more efficient and accurate selection of the boundary box around point cloud 810.
16. Claims 14 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Shen in view of Chuah in view of Yan and further in view of Kumar et al. (US Patent Application Publication No. 2017/0161911 A1)
17. Regarding Claim 14 (Previously presented), while the combination of Shen, Chuah, and Yan does not explicitly disclose, Kumar discloses The method of claim 1, wherein the rendered cropped volume is rendered using a neural rendering layer. (paragraph [0035] reciting “… Once the pixels of image 202 have been processed by the computational layers within neural network 200, neural network 200 outputs a first order tensor with five dimensions corresponding to the smallest bounding box around the object of interest, including the x and y coordinates of the center of the bounding box, the height of the bounding box, the width of the bounding box, and a probability that the bounding box is accurate. …”)
It would have been obvious to a person of ordinary skills in the before the effective filing date of the claimed invention to modify Shen, Chuah, and Yan with Kumar so the neural network is used to generate the bounding box around point cloud 810 of Shen. This is a beneficial modification since it allows the bounding box dimensions to be more efficiently and accurately generated.
18. Regarding Claim 18 (Previously presented), while the combination of Shen, Chuah, and Yan does not explicitly disclose, Kumar discloses The non-transitory computer-readable medium of claim 15, wherein the rendered cropped volume is rendered using a neural rendering layer. (paragraph [0035] reciting “… Once the pixels of image 202 have been processed by the computational layers within neural network 200, neural network 200 outputs a first order tensor with five dimensions corresponding to the smallest bounding box around the object of interest, including the x and y coordinates of the center of the bounding box, the height of the bounding box, the width of the bounding box, and a probability that the bounding box is accurate. …”)
It would have been obvious to a person of ordinary skills in the before the effective filing date of the claimed invention to modify Shen, Chuah, and Yan with Kumar so the neural network is used to generate the bounding box around point cloud 810 of Shen. This is a beneficial modification since it allows the bounding box dimensions to be more efficiently and accurately generated.
Allowable Subject Matter
19. Claims 3-4, 8-13, 16-17, and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
20. The following is a statement of reasons for the indication of allowable subject matter: Claim 3 recites the limitation wherein generating the first volume encompassing the first three-dimensional representation of the target object comprises: normalizing each image of the plurality of images to obtain a plurality of normalized images, comprising: centering the target object in the image using a cropping operation; and resizing the image to a predefined pixel size using an interpolation technique which is neither disclosed nor suggested by the cited references, either singly or in combination.
21. Claim 4 depends from claim 3.
22. Claim 8 recites the limitation providing the at least a subset of the plurality of images to a view generation engine, wherein the view generation engine generates a plurality of annotated synthetic images, wherein each annotated synthetic image is annotated with a respective point of view of the target object; and extrapolating the second volume from the plurality of annotated synthetic images which is neither disclosed nor suggested by the cited references, either singly or in combination.
23. Claims 9-13 depends from claim 8.24. Claim 16 recites the limitation providing the at least a subset of the plurality of images to a view generation engine, wherein the view generation engine generates a plurality of annotated synthetic images using one or more image-processing algorithms, wherein each annotated synthetic image is annotated with a respective point of view of the target object; and extrapolating the second volume from the plurality of annotated synthetic images which is neither disclosed nor suggested by the cited references, either singly or in combination.
25. Claim 17 depends from claim 16.
26. Claim 20 provide the at least a subset of the plurality of images to a view generation engine, wherein the view generation engine generates a plurality of annotated synthetic images using a NeRF algorithm configured to optimize a continuous volumetric scene function based on the plurality of images, wherein each annotated synthetic image is annotated with a respective point of view of the target object; and extrapolate the second volume from the plurality of annotated synthetic images which is neither disclosed nor suggested by the cited references, either singly or in combination.
Response to Arguments
27. Applicant’s arguments, see Remarks, filed 6/25/2026, with respect to the rejections of claims 1-2, 5-7, 14-15, and 18-19 under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Yan. Yan discloses that any virtual scene can be divided up in grids. Each grid cell corresponds to a voxel. Therefore, the virtual character head and space in Shen, which correspond to a virtual 3D scene, can be divided by grids forming voxels for the entire scene. A cropping of those voxels still contains a subset of those voxels. Therefore, the newly amended limitations to claims 1, 15, and 19 are rejected by Yan.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
CONTACT
Any inquiry concerning this communication or earlier communications from the examiner should be directed to FRANK S CHEN whose telephone number is (571)270-7993. The examiner can normally be reached Mon - Fri 8-11:30 and 1:30-6.
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, Kee Tung can be reached at 5712727794. 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.
/FRANK S CHEN/Primary Examiner, Art Unit 2611
Prosecution Insights