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 Rejections - 35 USC § 103
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 1-2 and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Fujioka (US 20240362822) in view of Luo (US 20240020788) and further in view of Rhoads (US 20190266749).
Regarding claim 1, Fujioka teaches a system for adding copyright protection to implicit 3D models, comprising:
A first multilayer perceptron (MLP) module configured to output a geometry parameter according to a 3D coordinate parameter obtained from a 3D model source (Paragraph 172, the MLP model of D-NeRF does not explicitly handle the refractive index and the incident angle, but directly learns positional shift (Δx, Δy, Δz) with respect to the three-dimensional coordinates (x, y, z) using the camera posture and histogram data (x, y, z, hst_cnt) as inputs);
A second MLP module configured to output a base-colors parameter according to a viewing-directions parameter obtained from the 3D model source and according to outcomes of the first MLP module (Paragraph 92, camera postures (x, y, z, θ, φ) at that time are input, and a function F of multilayer perceptron (MLP) that outputs luminance (RGB value)); Note: the x, y, z values that are the input to function F can be learned from the first MLP module.
While Fujioka fails to disclose the following, Luo teaches:
A color feature encoder configured to concatenate the geometry parameter, the viewing-directions parameter, and the base-colors parameter to obtain a spatial descriptor and further configured to transform the spatial descriptor to a high-dimensional color feature field (Paragraph 77, The message vector 504 can be first repeated along both spatial and temporal dimensions to the same size as each three-dimensional feature encoding 510A/510B, and can be concatenated with the feature map(s) three-dimensional feature encoding 510A/510B along the channel dimension to obtain three-dimensional fused encoding);
A message feature encoder configured to map messages to higher dimensions so as to obtain a message feature field (Paragraph 77, The message vector 504 can be scaled to the scale of the three-dimensional feature encoding 510A to obtain scaled message encoding);
A feature fusion module configured to generate a watermarked color representation and embed the watermarked color representation into the 3D model source (Paragraph 79, the embedding portion 509 can fuse the three-dimensional feature encodings 510A/510B with the scaled message embeddings 506A/506B).
Luo and Fujioka are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Fujioka to incorporate the teachings of Luo and use a color feature encoder, a message feature encoder, and a feature fusion module to generate and embed a watermark representation. Doing so would allow for copyrighting the 3D model source.
While the combination of Fujioka and Luo fails to disclose the following, Rhoads teaches:
A rendering module configured to query the watermarked color representation and the geometry parameter at a plurality of sampling points along one or more camera rays (Paragraph 87, Along each arc, 65,536 values are sampled from the tiled watermark signal, at points uniformly spaced along the arc) and to apply a rendering operator, based on the queried watermarked color representation and the queried geometry parameter, to generate a rendered image carrying an embedded message (Paragraph 135, This spatial position indicates the 4D pose of the captured image excerpt, relative to the camera. This information is then passed to a watermark decoder, which uses it to extract the payload bits encoded in the image excerpt—now that the geometry of the payload bits' representations in the image excerpt is understood). Note: Rhoads teaches sampling along arcs. A person of ordinary skill in the art would be able to apply this to sampling along camera rays.
Rhoads and the combination of Fujioka and Luo are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka and Luo to incorporate the teachings of Rhoads and query the watermarked color image and the geometry parameter at a plurality of sampling points alone one or more camera rays and generate a rendered image with an embedded image. Doing so would allow for efficiently decoding and displaying the watermark information.
Method claim 9 corresponds to system claim 1. Therefore, claim 9 is rejected for the same reasons as used above.
Regarding claim 2, the combination of Fujioka, Luo, and Rhoads teaches the system of claim 1. While the combination as presented previously fails to disclose the following, Luo further teaches:
Wherein the feature fusion module is further configured to employ the base-colors parameter, and the watermarked color representation and the base-colors parameter have the same dimension (Paragraph 77, The message vector 504 can be first repeated along both spatial and temporal dimensions to the same size as each three-dimensional feature encoding 510A/510B).
Luo and the combination of Fujioka and Rhoads are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka and Rhoads to incorporate the teachings of Luo and use the base-colors parameter and ensure the watermarked color representation and the base-colors parameter have the same dimension. Doing so would allow for easily concatenating or otherwise manipulating the input to the desired output.
Method claim 10 corresponds to system claim 2. Therefore, claim 10 is rejected for the same reasons as used above.
Claims 3 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Fujioka in view of Luo and further in view of Rhoads as applied to claims 1-2 and 9-10 above and further in view of Yoo (US 20230214953).
Regarding claim 3, the combination of Fujioka, Luo, and Rhoads teaches the system of claim 1. While the combination fails to disclose the following, Yoo teaches:
A message extractor comprising a convolutional neural network-based (CNN-based) network and configured to reveal the message from 2D rendered images in the 3D model source (Paragraph 21, the three-dimensional image data can be a 3D mesh (e.g., a polygonal mesh, etc.) and/or any materials associated with the 3D mesh (e.g., textures, 2D maps; Paragraph 23, convolutional neural networks).
Yoo and the combination of Fujioka, Luo, and Rhoads are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka, Luo, and Rhoads to incorporate the teachings of Yoo and extract 2D images from the 3D model source using a CNN. Doing so would allow for efficiently storing and transmitting additional data along with the 3D watermark.
Method claim 11 corresponds to system claim 3. Therefore, claim 11 is rejected for the same reasons as used above.
Claims 4 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Fujioka in view of Luo and further in view of Rhoads and further in view of Yoo as applied to claims 3 and 11 above and further in view of Wang (Deep 3D mesh watermarking with self-adaptive robustness).
Regarding claim 4, the combination of Fujiko, Luo, Rhoads, and Yoo teaches the system of claim 3. While the combination fails to disclose the following, Wang teaches:
Wherein the message extractor employs a sequence of 2D convolutional layers with batch normalization and Rectified Linear Unit (ReLU) functions, and the message extractor incorporates average pooling and a final linear layer with a fixed output dimension, which corresponds to the length of the message, so as to produce a continuous predicted message (Page 4, Column 2, Paragraph 3, Then we define the graph residual block consisting of two GraphConv+BatchNorm+ReLU blocks with a short connection (He et al. 2016), as shown in Fig. 2. For the initial block of the embedding sub-network and extracting sub-network, the input feature is the 3D coordinates of vertices and outputs 64-dim feature. For other blocks, the output feature has the same shape as the input feature with 64 dimensions; Page 6, Paragraph 3, Followed by the global average pooling layer and a two-layer fully connected layer (MLP), the extracted watermark wext is obtained).
Wang the combination of Fujioka, Luo, Rhoads, and Yoo are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka, Luo, Rhoads, and Yoo to incorporate the teachings of Wang use batch normalization and ReLU, and use average pooling and a final linear layer with a fixed output dimension. Doing so would allow for defending against reordering attack.
Method claim 12 corresponds to system claim 4. Therefore, claim 12 is rejected for the same reasons as used above.
Claims 6 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Fujioka in view of Luo and further in view of Rhoads as applied to claims 1-2 and 9-10 above and further in view of Jang (Cropping-resilient 3D mesh watermarking based on consistent segmentation and mesh steganalysis).
Regarding claim 6, the combination of Fujioka, Luo, and Rhoads teaches the system of claim 1. While the combination fails to disclose the following, Jang teaches:
Wherein the rendering module utilizes patch-level rendering and is further configured to crop a window from an image of the 3D model source at a random position and to uniformly sample pixels from the window to create a smaller patch (Page 5, First, surface-type segmentation employs surface geometric properties of the mesh such as planarity or curvature to create surface patches).
Jang and the combination of Fujioka, Luo, and Rhoads are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka, Luo, and Rhoads to incorporate the teachings of Jang and create patches from the image of the 3D model. Doing so would allow for creating a watermark that is resistant to attack.
Method claim 14 corresponds to system claim 6. Therefore, method claim 14 is rejected for the same reasons as used above.
Claims 7 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Fujioka in view of Luo and further in view of Rhoads as applied to claims 1-2 and 9-10 above and further in view of Jang.
Regarding claim 7, the combination of Fujioka, Luo, and Rhoads teaches the system of claim 1. While the combination fails to disclose the following, Jang teaches:
Wherein the feature fusion module is further configured to incorporate spatial information into the watermarked color representation, such that the messages embedded in the watermarked color representation remains consistent across different viewpoints rendered from the 3D model source (Section 6.2, The proposed watermark is experimentally invariant to the content preserving attacks including vertex/face reordering in the mesh and similarity transformation (i.e. rotation, scaling, translation (RST) and their combination) because we employ vertex norms which are RST invariant features).
Jang and the combination of Fujioka, Luo, and Rhoads are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka, Luo, and Rhoads to incorporate the teachings of Jang and keep the watermark consistent across viewpoints rendered. Doing so would allow for a standardized watermark that is resistant to attack.
Method claim 15 corresponds to system claim 7. Therefore, method claim 15 is rejected for the same reasons as used above.
Claims 8 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Fujioka in view of Luo and further in view of Rhoads as applied to claims 1-2 and 9-10 above and further in view of Miller (US 20130120369).
Regarding claim 8, the combination of Fujioka, Luo, and Rhoads teaches the system of claim 1. While the combination fails to disclose the following, Miller teaches:
A display configured display the 3D model sources without embedding the watermarked color representation and with embedding the watermarked color representation (Paragraph 64, permission to remove watermarks from renderings of models based on the initial 3D model).
Miller and the combination of Fujioka, Luo, and Rhoads are both considered to be analogous to the claimed invention because they are in the same field of 3D watermarking. Therefore, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combination of Fujioka, Luo, and Rhoads to incorporate the teachings of Miller and display the 3D model sources with and without the watermark. Doing so would allow for customizing the display based on associated permissions.
Method claim 16 corresponds to system claim 8. Therefore, claim 16 is rejected for the same reasons as used above.
Response to Amendment
Applicant’s arguments with respect to claims 1 and 9 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Rhoads teaches the newly added limitation of these claims by teaching sampling points along a ray and generating a rendered image with the embedded message. It would have been obvious to a person of ordinary skill in the art to combine these teachings with the teachings of Fujioka and Lou.
Additionally, applicant argues that Fujioka and Luo cannot be combined due to operating on different data representations. However, although Lou operates on video data, it teaches processing a plurality of video frames or images. Both Fujioka and Luo teach watermarking in 3D images. Therefore, it would have been obvious a person of ordinary skill in the art to combine the teachings of Fujioka and Lou.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SNIGDHA SINHA whose telephone number is (571)272-6618. The examiner can normally be reached Mon-Fri. 12pm-8pm.
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, Jason Chan can be reached at 571-272-3022. 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.
/SNIGDHA SINHA/Examiner, Art Unit 2619
/JASON CHAN/Supervisory Patent Examiner, Art Unit 2619
Prosecution Insights