DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Notice to Applicants
This action is in response to the amendments and remarks filed on 12/19/2025.
Claims 8-11 and 13 are pending.
Corrective Actions by Applicant
Claims 8-9 and 11 have been amended.
Claim 12 has been canceled.
Response to Arguments
The examiner has fully considered Applicant’s presented arguments.
On page 5 of the remarks, Applicant argues that amended claim 8 is directed to patent-eligible subject matter under 35 U.S.C. 101. This is persuasive. All 35 U.S.C. 101 rejections have been withdrawn.
On pages 6-8 of the remarks, Applicant argues that Rosewarne fails to disclose every element of amended claim 8. This is persuasive. All previous 35 U.S.C. 102 rejections have been withdrawn. However, the claim amendments necessitate new 35 U.S.C. 103 rejections below.
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 8-11 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Rosewarne et al. (U.S. Publ. US-2024/0205402-A1) in view of Zhang et al. (U.S. Publ. US-2021/0314573-A1).
Regarding claim 8, Rosewarne discloses a decoding method (see figures 7-8, 16, and paragraphs 0046-0047 and 0057), comprising:
generating packed feature maps by decoding an input bitstream (first see figure 7, where bitstream 143 is input to the video decoder 144; then see figure 14 and paragraph 0167, which specify that the bitstream 143 of figure 7 contains encoded, packed feature maps; finally see figure 11 and paragraph 0161, which show an example set of packed feature maps);
and generating a multi-resolution feature map by performing unpacking on the packed feature maps (see figure 8 and paragraph 0153, where the decoded frames 147 are input to the unpacker module 810, which extracts packed feature maps from each frame to produce unpacked feature maps),
wherein the multi-resolution feature map includes a high-resolution feature map and a low-resolution feature map (figure 11 and paragraph 0161 show example packed feature maps that have various resolutions; paragraph 0069 specifies how each set of feature maps has a different spatial resolution).
Rosewarne fails to disclose and the input bitstream includes a residual value between an original low-resolution feature map and a compensation feature map generated by encoding and then decoding the original low-resolution feature map, and wherein the high-resolution feature map is configured such that compression damage, corresponding to the compensation feature map, is compensated using the residual value.
More specifically, paragraph 0014 of Rosewarne specifies that the residual values represent the difference between original and encoded-decoded values, which when added back to the higher-resolution feature maps serves to compensate for information lost during encoding and decoding; however, Rosewarne merely fails to disclose that the residuals are between two feature maps of the same resolution.
Pertaining to the same field of endeavor, Zhang discloses and the input bitstream includes a residual value between an original low-resolution feature map and a compensation feature map generated by encoding and then decoding the original low-resolution feature map (see figure 9 and paragraph 0091, where residual features 724 are obtained from the difference 720 between original features 713 and base features 717 obtained from encoding and decoding an input video 701),
and wherein the high-resolution feature map is configured such that compression damage, corresponding to the compensation feature map, is compensated using the residual value (see figure 9 and paragraph 0094, where the residual features 742 and upsampled 746 original features 747 are added together 748 to improve image quality; see figure 9 and paragraphs 0056 and 0123-0124, where the summed features are additionally input to an enhancement neural network 790 that performs various enhancements, such as super-resolution to create a higher-resolution feature map).
Rosewarne and Zhang are considered analogous art, as they are both directed to neural networks for enhanced image coding. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have integrated the teachings of Zhang into Rosewarne because doing so minimizes the loss of data created by image compression (see Zhang paragraphs 0078-0080).
Regarding claim 9, Rosewarne in view of Zhang discloses wherein the high-resolution feature map is adjusted by upsampling the residual value and by using the upsampled residual value (see Rosewarne figure 4 and paragraph 0102, where the alternative residual network 400 applies summation modules 460, 462, and 464 to add upsampled residuals 451, 453, and 455 to higher-resolution feature maps 443, 445, and 447 to adjust the higher-resolution feature maps).
Regarding claim 10, Rosewarne in view of Zhang discloses wherein the upsampling is performed based on a double cubic interpolation method, a bilinear interpolation method, a nearest neighbor pixel interpolation method, or a deep learning-based interpolation method (see Rosewarne paragraph 0102, where nearest neighbor interpolation is used for low computational complexity).
Regarding claim 11, Rosewarne in view of Zhang discloses wherein the high-resolution feature map is generated using the low-resolution feature map (see Rosewarne figure 4 and paragraph 0102, where the residual values from the lower-resolution feature maps are added to the higher-resolution feature maps).
Regarding claim 13, Rosewarne in view of Zhang discloses wherein generating the multi-resolution feature map comprises: separating (see Rosewarne figure 8, decoded metadata 155, feature map groups 820 and paragraphs 0153-0154, where the decoded metadata indicates which group each unpacked feature map belongs to, allowing for unique processing, such as quantization, to be applied differently to each group; figure 14 and paragraph 0169 specify how the bitstream encodes the feature map groupings) and inversely aligning the packed feature maps (see Rosewarne figure 7, Inverse primary transform 744 and paragraphs 0146-0147, where an inverse discrete cosine transform is applied to the decoded features to convert them from the frequency domain back to the spatial domain).
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 Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICHOLAS JOHN HELCO whose telephone number is (703)756-5539. The examiner can normally be reached on Monday-Friday from 9:00 AM to 5:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella, can be reached at telephone number 571-272-7778. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/NICHOLAS JOHN HELCO/Examiner, Art Unit 2667
/MATTHEW C BELLA/Supervisory Patent Examiner, Art Unit 2667