DETAILED ACTION
Claims 1-20 are pending for examination.
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 .
Priority
Acknowledgment is made of applicant's claim under US PRO 63/424427 filed on 11/10/2022.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-7 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Li et al, E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context.
Regarding Claim 1, Li discloses a system comprising:
a matrix expansion block configured to construct a matrix representation of an input sequence (Li p.6 [Fig.2] – representation Rd of the input sequence is a matrix of dimensions 1xd);
a component merging block configured to merge the matrix representation with a grid (Li P.6-7 [Fig.2, Eq.3] – The operator merges the two components for input to network F(theta));
an encoder configured to receive an output of the component merging block (Li p.11 [sec5.4] – an encoder is used in MLPs and the alternative to remove redundancy and conduct fusion (F(theta)) in E-NeRV-MLP);
a convolution stage configured to generate, using an output of the encoder, a multi-component representation of an output corresponding to the input sequence (Li p.11 [sec5.4] – the second of the consecutive MLPs); and
a convolutional upscaling stage configured to produce, using the multi-component representation of the output, an output sequence corresponding to the input sequence (Li Fig.2 – see Blocks x5; and Fig.8 – see temporal instance normalization module).
Regarding Claim 2, Li discloses the system of claim 1, wherein the multi-component representation of the output corresponding to the input sequence is compressed in comparison with the matrix representation of the input sequence (Li Fig.2 – see Blocks x5; and Fig.8 – see temporal instance normalization module).
Regarding Claim 3, Li discloses the system of claim 1, wherein the input sequence and the output sequence comprise video sequences (Li p.1 – see Abstract for output of video frames).
Regarding Claim 4, Li discloses the system of claim 1, wherein the grid comprises a fixed coordinate grid (Li Fig.2 and p.7 – we initialize it using the normalized grid coordinates).
Regarding Claim 5, Li discloses the system of claim 1, wherein the encoder comprises a positional encoder (Li S.3, p.5 – Eq2 uses positional encoding).
Regarding Claim 6, Li discloses the system of claim 1, wherein the convolution stage comprises a spatial-temporal convolution stage (Li p.11 [sec5.4] – see E-NeRV-MLP).
Regarding Claim 7, Li discloses the system of claim 1, wherein the multi-component representation of the output corresponding to the input sequence comprises a spatial-temporal representation of the output (Li Eq.3 – equation 3 proposes to disentangle the spatial-temporal information).
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.
Claim(s) 8 is rejected under 35 U.S.C. 103 as being unpatentable over Li, in view of Sicheng, [INVR] Review of related technology in INVR.
Regarding Claim 8, Li discloses the system of claim 1, as outlined above.
However, Li does not explicitly disclose the multi-component representation of the output corresponding to the input sequence comprises a multi-view representation.
Sicheng teaches the multi-component representation of the output corresponding to the input sequence comprises a multi-view representation (Sicheng p.4 [sec3.1] – Implicit neural 3D video representation is able to synthesize novel views of a dynamic scene from a single monocular video captured by a moving camera or limited multi-view videos. Once the representation is trained with the supervision of input views, it could be used to render into a novel camera trajectory to generate a different photorealistic video sequence from novel views).
Therefore, it 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 to modify Li to have a multi-view representation, as taught by Sicheng. One would be motivated as the multi-view representation can take the different inputs to allow for multiple views to be seen from a video sequence.
Claim(s) 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Li, in view of Olivier et al, US 2024/0249489 A1.
Regarding Claim 9, Li discloses the system of claim 1, as outlined above.
However, Li does not explicitly disclose the convolutional upscaling stage includes a plurality of upscaling blocks each comprising an adaptive instance normalization (AdaIN) module.
Olivier teaches the convolutional upscaling stage includes a plurality of upscaling blocks each comprising an adaptive instance normalization (AdaIN) module (Olivier [0049] – An example of architecture of the decoder is illustrated in FIG. 2 wherein a first module of the decoder (upper part) comprises 6 layers with 2 layers of adaptive instance normalization and 4 convolutional layers wherein Conv-X indicates a number of X convolution filters used in a layer followed by an upscaling and activation layers).
Therefore, it 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 to modify Li to include a plurality of upscaling blocks each comprising an adaptive instance normalization (AdaIN) module, as taught by Olivier. One would be motivated as the module can be used to apply a style without requiring a system to be retrained for said style/features.
Regarding Claim 10, Lin, in combination, further discloses the system of claim 9, wherein each of the plurality of upscaling blocks further comprising a multilayer perceptron (Li p.21, Fig.8 – The brown arrows indicate the MLP layers for temporal instance normalization… see Fig. 8 was a comparison of the convolution stage).
Claim(s) 11-14 are rejected under 35 U.S.C. 103 as being unpatentable over Li, in view of Hemmer et al, US 2020/0099954 A1.
With regard to claim 11, the claim limitations are similar in concept in claim 1 but in a different embodiment.
Claim 11 also contains limitations claiming a neural network and the concepts of modeling an input, compressing the neural network representation and generating a compressed output sequence.
However, Li does not explicitly disclose the limitations unique to claim 11.
Hemmer teaches claiming a neural network and the concepts of modeling an input, compressing the neural network representation and generating a compressed output sequence (Hemmer [0135] – neural network decoder 515 can be configured to use the variables of a corresponding one of the latent representations for 3D objects 510 to reproduce an approximation of a shape and/or a model of the 3D object before the 3D object was compressed by the neural network encoder 505. The neural network decoder 515 can be configured to generate an approximation of the 3D model corresponding to one of the stored 3D objects 135).
Therefore, it 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 to modify Li to generate a compressed output sequence, as taught by Hemmer. One would be motivated as the compressed neural network reduces the processing power to model the input.
Regarding Claim 12, Li, in combination, further discloses the method of claim 11, wherein the input sequence and the output sequence comprise video sequences (Li p.1 – see Abstract for output of video frames).
Regarding Claim 13, Li and Hemmer teach the method of claim 12, as outlined above.
However, Li does not explicitly disclose the neural network representation of the input sequence is compressed using entropy encoding.
Hemmer teaches the neural network representation of the input sequence is compressed using entropy encoding (Hemmer [0045] – Compressing the frame 110 can include a prediction step, a quantization step, a transformation step and an entropy encoding step).
Therefore, it 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 to modify Li to use entropy encoding, as taught by Hemmer. One would be motivated as entropy encoding reduces the amount of data generated in the bitstream.
Regarding Claim 14, Li and Hemmer teach the method of claim 11, as outlined above.
However, Li does not explicitly disclose the NN comprises one or more convolutional neural networks (CNNs).
Hemmer teaches the NN comprises one or more convolutional neural networks (CNNs) (see CNN in Hemmer [0126]).
Therefore, it 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 to modify Li to use a CNN, as taught by Hemmer. One would be motivated as the convolutional NNs use patterns to reduce processing power.
Allowable Subject Matter
Claims 15 and 16 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.
Claims 17-20 are allowed.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMIR SHAHNAMI whose telephone number is (571)270-0707. The examiner can normally be reached Monday - Friday 8:00 am to 4:00 pm.
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, Joseph Ustaris can be reached at 571-272-7383. 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.
/AMIR SHAHNAMI/ Primary Examiner, Art Unit 2483
Prosecution Insights