DETAILED ACTION
1. The Office Action is in response to Application 19239741 filed on 06/16/2025. Claims 1-20 are pending.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statements (IDS) submitted on 06/16/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in Application 19239741 filed on 06/16/2025.
Priority # Filling Data Country
202310430930.X 2023-04-14 CN
Claim Rejections - 35 USC § 112
11. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
12. Claim 1 and its dependent claims 2-12 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
For claim 1, it recites limitations of “a chrominance filtering block” in “and inputting, based on the determined target filtering order, the first chrominance component and the second chrominance component of the current block into a neural network filter to obtain a chrominance filtering block of the current block”; However, it is not clear what is the meaning of “a chrominance filtering block” of a current block; since first, after inputting the first chrominance component and the second chrominance component of the current block into a neural network filter, the first chrominance component and the second chrominance component is “filtered” components instead of “filtering component”; second, is the chrominance filtering block the same size of the current block or not?; third, since there are two chrominance components have been filtered, how can there is only one chrominance filtering block after the two chrominance components have been filtered? What is the relationship between the two chrominance components and the chrominance filtering block?
Thus the scope of the claim and its dependent claim 2-12 are unclear.
13. Claim 13 and its dependent claims 14-17 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention for the similar reason for independent claim 1 and its claim 2-12.
14. Claim 19 and its dependent claim 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention for the similar reason for independent claim 1 and its claim 2-12.
12. Claim 5 and its dependent claims 6-7 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
For claim 5, it recites limitations of “the second filtering costs” in “and determining the target filtering order from the plurality of filtering orders based on the second filtering costs corresponding to the plurality of filtering orders”; However, it is not clear the second filtering costs is “an i-th second filtering cost of the neighboring filtered area in the i-th filtering order” or second filtering cost of the current block (since claim 3, which claim 5 depends on, has filtering cost of the plurality of filtering orders for the current block only)?
Thus the scope of the claim and its dependent claim 6-7 are unclear.
12. Claim 18 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
For claim 18, it recites limitations of “second filtering costs” in “and determining the target filtering order from the plurality of filtering orders based on second filtering costs corresponding to the plurality of filtering orders”; However, it is not clear the second filtering costs is “an i-th second filtering cost of the neighboring filtered area in the i-th filtering order” or second filtering cost of the current block (since claim 14, which claim 18 depends on, has filtering cost of the plurality of filtering orders for the current block only)?
Thus the scope of the claim is unclear.
Claim Rejections - 35 USC § 102
8. 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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
9. Claims 1-4, 8-17, 19-20 are rejected under 35 U.S.C. 102 (a) (1) as being anticipated by DAI (WO 2024077574).
Regarding claim 1, DAI teaches a picture filtering method (fig. 7) of a decoder (fig. 1C), the method comprising:
reconstruct a current picture (as shown in fig. 1C) that is encoded in a coded bitstream (the input to component 15, fig. 1C);
determine, for a current block in the reconstructed current picture (fig. 5, in which, UV are first and second chrominance component in reconstructed current block; page 13, … the luminance component and chrominance component of the reconstructed image are input separately, as shown in Figure 4C, and two models need to be trained…), a target filtering order from a plurality of filtering orders of a first chrominance component and a second chrominance component of the current block (fig. 4C, in which, NNLF2 model 1 and mode 2 are a plurality of filtering orders of a first chrominance component and a second chrominance component of the current block; and in fig. 6, a targeted filtering order is selected based on minimum distortion; page 13-14, …in NNLF1` and NNLF2, for the luminance component and chrominance component of the reconstructed image input into the neural network, NNLF1 adopts a joint input method, as shown in Figure 3C, and only one network model needs to be trained; in NNLF2, the luminance component and chrominance component of the reconstructed image are input separately, as shown in Figure 4C, and two models need to be trained. For the two chrominance components, namely the U component and the V component, NNLF1` and NNLF2 both adopt a joint input method…S110, calculating a rate-distortion cost of performing NNLF on an input reconstructed image using a first mode, and a rate-distortion cost of performing NNLF on the reconstructed image using a second mode;
S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image);
and input, based on the determined target filtering order, the first chrominance component and the second chrominance component of the current block into a neural network filter to obtain a chrominance filtering block of the current block (as shown in fig. 12A/12B, NNLF model is a neural network filter and the two chrominance components are input into it and a chrominance filtering block is obtained; page 19, …As shown in Figure 12A, for a certain NNLF filter, when using the first mode, the arrangement order of its input information can be {recY, recU, recV, predY, predU, predV, baseQP, sliceQP, slicetype,.Math.}, and the arrangement order of its output information can be {cnnY, cnnU, cnnV}, where rec represents the reconstructed image).
Regarding claim 13, DAI teaches a picture filtering method (fig. 7) of a encoder (fig. 1B), the method comprising:
encoding a current picture (as shown in fig. 1B)
reconstruct a current picture (as shown in fig. 1C) that is encoded in a coded bitstream (the input to component 15, fig. 1C);
determine, for a current block in the reconstructed current picture (fig. 5, in which, UV are first and second chrominance component in reconstructed current block; page 13, … the luminance component and chrominance component of the reconstructed image are input separately, as shown in Figure 4C, and two models need to be trained…), a target filtering order from a plurality of filtering orders of a first chrominance component and a second chrominance component of the current block (fig. 4C, in which, NNLF2 model 1 and mode 2 are a plurality of filtering orders of a first chrominance component and a second chrominance component of the current block; and in fig. 6, a targeted filtering order is selected based on minimum distortion; page 13-14, …in NNLF1` and NNLF2, for the luminance component and chrominance component of the reconstructed image input into the neural network, NNLF1 adopts a joint input method, as shown in Figure 3C, and only one network model needs to be trained; in NNLF2, the luminance component and chrominance component of the reconstructed image are input separately, as shown in Figure 4C, and two models need to be trained. For the two chrominance components, namely the U component and the V component, NNLF1` and NNLF2 both adopt a joint input method…S110, calculating a rate-distortion cost of performing NNLF on an input reconstructed image using a first mode, and a rate-distortion cost of performing NNLF on the reconstructed image using a second mode;
S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image);
and input, based on the determined target filtering order, the first chrominance component and the second chrominance component of the current block into a neural network filter to obtain a chrominance filtering block of the current block (as shown in fig. 12A/12B, NNLF model is a neural network filter and the two chrominance components are input into it and a chrominance filtering block is obtained; page 19, …As shown in Figure 12A, for a certain NNLF filter, when using the first mode, the arrangement order of its input information can be {recY, recU, recV, predY, predU, predV, baseQP, sliceQP, slicetype,.Math.}, and the arrangement order of its output information can be {cnnY, cnnU, cnnV}, where rec represents the reconstructed image).
Regarding claim 19, DAI teaches a decoding apparatus (fig. 1C), comprising:
processing circuitry (fig. 1C, 150, decoding unit) configured to:
reconstruct a current picture (as shown in fig. 1C) that is encoded in a coded bitstream (the input to component 15, fig. 1C);
determine, for a current block in the reconstructed current picture (fig. 5, in which, UV are first and second chrominance component in reconstructed current block; page 13, … the luminance component and chrominance component of the reconstructed image are input separately, as shown in Figure 4C, and two models need to be trained…), a target filtering order from a plurality of filtering orders of a first chrominance component and a second chrominance component of the current block (fig. 4C, in which, NNLF2 model 1 and mode 2 are a plurality of filtering orders of a first chrominance component and a second chrominance component of the current block; and in fig. 6, a targeted filtering order is selected based on minimum distortion; page 13-14, …in NNLF1` and NNLF2, for the luminance component and chrominance component of the reconstructed image input into the neural network, NNLF1 adopts a joint input method, as shown in Figure 3C, and only one network model needs to be trained; in NNLF2, the luminance component and chrominance component of the reconstructed image are input separately, as shown in Figure 4C, and two models need to be trained. For the two chrominance components, namely the U component and the V component, NNLF1` and NNLF2 both adopt a joint input method…S110, calculating a rate-distortion cost of performing NNLF on an input reconstructed image using a first mode, and a rate-distortion cost of performing NNLF on the reconstructed image using a second mode;
S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image);
and input, based on the determined target filtering order, the first chrominance component and the second chrominance component of the current block into a neural network filter to obtain a chrominance filtering block of the current block (as shown in fig. 12A/12B, NNLF model is a neural network filter and the two chrominance components are input into it and a chrominance filtering block is obtained; page 19, …As shown in Figure 12A, for a certain NNLF filter, when using the first mode, the arrangement order of its input information can be {recY, recU, recV, predY, predU, predV, baseQP, sliceQP, slicetype,.Math.}, and the arrangement order of its output information can be {cnnY, cnnU, cnnV}, where rec represents the reconstructed image).
Regarding claim 2, DAI teaches the limitations recited in claim 1 as discussed above. In addition, DAI further discloses that obtaining order information from the coded bitstream (fig. 6, model 1 and mode 2 are order information and it is obtained from coded bitstream; page 20, … the first flag is a picture-level syntax element or a block-level syntax element… the second mode is a chromaticity information adjustment mode; the first flag is used to indicate whether to perform chromaticity information adjustment when performing NNLF on the reconstructed image), the order information indicating the target filtering order (as shown in fig. 6 and fig. 7, model 1/model 2; NNLF-A, NNLF-B (their index) represent order information); and determining the target filtering order based on the order information (fig. 6, step S120; page 013, …. S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image ).
Regarding claim 3, DAI teaches the limitations recited in claim 2 as discussed above. In addition, DAI further discloses that determining the target filtering order based on filtering costs of the plurality of filtering orders (fig. 6, step S120; page 013, …. S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image ).
Regarding claim 4, DAI teaches the limitations recited in claim 3 as discussed above. In addition, DAI further discloses that wherein the filtering costs include first filtering costs (fig. 6, in which, the rate-distortion cost for model 1 is interpreted as the first filtering costs) ; the target filtering order is determined based on a first filtering cost of each of the plurality of filtering orders, the first filtering cost of the respective filtering order being determined based on the first chrominance component and the second chrominance component of the current block being inputted into the neural network filter in the respective filtering order; and the target filtering order has a smallest first filtering cost in the plurality of filtering orders (as shown in fig. 6, step S110-S120; page 013, ….S110, calculating a rate-distortion cost of performing NNLF on an input reconstructed image using a first mode, and a rate-distortion cost of performing NNLF on the reconstructed image using a second mode… S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image).
Regarding claim 8, DAI teaches the limitations recited in claim 1 as discussed above. In addition, DAI further discloses that the plurality filtering orders include a first filtering order and a second filtering order (fig. 6, in which, first filtering order is using model 1 and second one is using model 2);
the first filtering order is that the first chrominance component is input before the second chrominance component into the neural network filter (as shown in fig. 5 and fig. 6, in which, the first chrominance component U can be input before the second chrominance component V); and the second filtering order is that the second chrominance component is input before the first chrominance component into the neural network filter (as shown in fig. 5 and fig. 6, in which, the second chrominance component V can be input before the first chrominance component U; also, fig. 12A and fig. 12B shows the order difference).
Regarding claim 9, DAI teaches the limitations recited in claim 1 as discussed above. In addition, DAI further discloses that the current block is at least one coding tree unit (CTU) of the reconstructed current picture or a preset picture area of the reconstructed current picture (page 8, … The division unit 101 is configured to cooperate with the prediction unit 100 to divide the received video data into slices, coding tree units (CTUs)).
Regarding claim 10, DAI teaches the limitations recited in claim 1 as discussed above. In addition, DAI further discloses that the neural network filter is trained with at least one CTU as a training unit or a preset picture area as the training unit (fig. 1B, division unit 101; page 19, … NNLF processing may also be performed based on other coding units such as blocks (such as CTU).
Regarding claim 11, DAI teaches the limitations recited in claim 1 as discussed above. In addition, DAI further discloses that wherein the neural network filter is trained based on a plurality of training orders (as shown in fig. 7, it can uses NNLF-A or NNLF-B; page 19, …. NNLF processing is performed based on the reconstructed image of the current frame. In other embodiments, NNLF processing may also be performed based on other coding units such as blocks (such as CTU) and slices in the current frame.
As shown in Figure 12A, for a certain NNLF filter, when using the first mode, the arrangement order of its input information can be {recY, recU, recV, predY, predU, predV, baseQP, sliceQP, slicetype,.Math.}, and the arrangement order of its output information can be {cnnY, cnnU, cnnV}, where rec represents the reconstructed image, pred represents the predicted image, and cnn represents the output filtered image.
When the second mode for adjusting chrominance information is used, the order of filter input information is adjusted to {recY, recV, recU, predY, predV, predU, baseQP, sliceQP, slicetype, ...}, and the order of output network information is adjusted to {cnnY, cnnV, cnnU}, as shown in FIG12B).
Regarding claim 12, DAI teaches the limitations recited in claim 1 as discussed above. In addition, DAI further discloses that wherein the plurality of training orders includes a first training order (fig. 12A) and a second training order (fig. 12B); the first training order is that the first chrominance component is input before the second chrominance component into the neural network filter (as shown in fig. 12A, U is before V); and the second training order is that the second chrominance component is input before the first chrominance component into the neural network filter (as shown in fig. 12B, V is before U; page 19, As shown in Figure 12A, for a certain NNLF filter, when using the first mode, the arrangement order of its input information can be {recY, recU, recV, predY, predU, predV, baseQP, sliceQP, slicetype,.Math.}, and the arrangement order of its output information can be {cnnY, cnnU, cnnV}, where rec represents the reconstructed image, pred represents the predicted image, and cnn represents the output filtered image.
When the second mode for adjusting chrominance information is used, the order of filter input information is adjusted to {recY, recV, recU, predY, predV, predU, baseQP, sliceQP, slicetype, ...}, and the order of output network information is adjusted to {cnnY, cnnV, cnnU}, as shown in FIG12B)).
Regarding claim 14, DAI teaches the limitations recited in claim 13 as discussed above. In addition, DAI further discloses that determining the target filtering order based on filtering costs of the plurality of filtering orders (fig. 6, step S120; page 013, …. S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image ).
Regarding claim 15, DAI teaches the limitations recited in claim 13 as discussed above. In addition, DAI further discloses that inputting, for a j-th filtering order in the plurality of filtering orders (as shown in fig. 12A/12B), the first chrominance component and the second chrominance component of the current picture block into the neural network filter according to the j-th filtering order to determine a j-th first filtering cost of the current picture block in the j-th filtering order, j being a positive integer less than or equal to a number N of the plurality of filtering orders (fig. 6, in which, the rate-distortion cost for model 1 is interpreted as the first filtering costs and the rate-distortion cost for model 2 is interpreted as the second filtering costs; it is obvious that j is a positive integer less than or equal of the total number (N) of the filtering orders); and determining the target filtering order from the plurality of filtering orders based on first filtering costs corresponding to the plurality of filtering orders (as shown in fig. 6, step S110-S120; page 013, ….S110, calculating a rate-distortion cost of performing NNLF on an input reconstructed image using a first mode, and a rate-distortion cost of performing NNLF on the reconstructed image using a second mode… S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image).
Regarding claim 16, DAI teaches the limitations recited in claim 15 as discussed above. In addition, DAI further discloses that inputting the first chrominance component and the second chrominance component of the current block into the neural network filter according to the j-th filtering order to obtain a j-th chrominance filtering block of the current block (as shown in fig. 12A/12B), and determining the j-th first filtering cost based on the j-th chrominance filtering block and an original block of the current block (fig. 6, in which, the rate-distortion cost for model 1 is interpreted as the first filtering costs and the rate-distortion cost for model 2 is interpreted as the second filtering costs); and the determining the target filtering order from the plurality of filtering orders based on the first filtering costs comprises: determining the filtering order having a smallest first filtering cost in the plurality of filtering orders as the target filtering order (as shown in fig. 6, step S110-S120; page 013, ….S110, calculating a rate-distortion cost of performing NNLF on an input reconstructed image using a first mode, and a rate-distortion cost of performing NNLF on the reconstructed image using a second mode… S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image).
Regarding claim 17, DAI teaches the limitations recited in claim 15 as discussed above. In addition, DAI further discloses that encoding order information into a bitstream of the current block (fig. 1B; page 20, … the first flag is a picture-level syntax element or a block-level syntax element… the second mode is a chromaticity information adjustment mode; the first flag is used to indicate whether to perform chromaticity information adjustment when performing NNLF on the reconstructed image), the order information indicating the target filtering order (as shown in fig. 6 and fig. 7, model 1/model 2; NNLF-A, NNLF-B (their index) represent order information).
Regarding claim 20, DAI teaches the limitations recited in claim 19 as discussed above. In addition, DAI further discloses that determine, for the current block in the reconstructed current picture, the target filtering order from the plurality of filtering orders based on one of (i) first information in the coded bitstream that indicates the target filtering order and (ii) filtering costs of the plurality of filtering orders (fig. 6, model 1 and mode 2 are order information and it is obtained from coded bitstream; page 20, … the first flag is a picture-level syntax element or a block-level syntax element… the second mode is a chromaticity information adjustment mode; the first flag is used to indicate whether to perform chromaticity information adjustment when performing NNLF on the reconstructed image; fig. 6, step S120; page 013, …. S120, determining to use a mode with the lowest rate-distortion cost between the first mode and the second mode to perform NNLF on the reconstructed image ).
11. Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See form 892.
12. Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZAIHAN JIANG whose telephone number is (571)272-1399. The examiner can normally be reached on flexible.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Sath Perungavoor can be reached on (571)272-7455. The fax phone number for the organization where this application or proceeding is assigned is 571-270-0655.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ZAIHAN JIANG/Primary Examiner, Art Unit 2488
Prosecution Insights