# US 2026/0019645 A1 · Tool selection for feature map encoding vs regular video encoding

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0019645 A1
- Document ID: US20260019645A1
- Status: Published application
- Kind: A1
- Application number: 19/336,992
- Filed: 2025-09-23
- Published: 2026-01-15
- Earliest claimed: 2021-04-07
- Assignees: Canon Kabushiki Kaisha
- Applicants: Canon Kabushiki Kaisha
- Inventors: Christopher James Rosewarne
- Web page: https://patentgrep.com/patent/US20260019645A1

## CPC

- H04N 19/70: characterised by syntax aspects related to video coding, e.g. related to compression standards
- H04N 19/85: using pre-processing or post-processing specially adapted for video compression
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06V 10/771: Feature selection, e.g. selecting representative features from a multi-dimensional feature space
- G06V 10/82: using neural networks
- H04N 19/46: Embedding additional information in the video signal during the compression process (H04N19/517, H04N19/68, H04N19/70 take precedence)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An apparatus for generating first encoded data and second encoded data. The apparatus comprises a determining unit for determining whether the apparatus generates encoded data including encoded data of a feature map based on a neural network. The apparatus also comprise an encoding unit for generating the first encoded data using a plurality of functions for encoding video data, in a case where the apparatus generates the first encoded data in a form of encoded video data not including the encoded data of the feature map. The encoding unit generates the encoded data of the feature map using a first part of the plurality of functions but not using a second part of the plurality of functions, in a case where the apparatus generates the second encoded data including the encoded data of the feature map.

## Claims

### Claim 1

An encoding apparatus comprising:
a determining unit for determining whether to generate encoded data of a frame where a plurality of feature maps obtained based at least on processing an input image by a neural network is arranged; and
an encoding unit for generating encoded data of an input image using a plurality of functions including at least deblocking filter in a case where the encoded data of the input image is to be generated instead of the frame where the plurality of feature maps is arranged,
wherein in a case where it is determined that the encoded data of the frame, where the plurality of feature maps is arranged, is to be generated, the encoding unit uses a first part of the plurality of functions but does not use a second part of the plurality of functions including the deblocking filter.

### Claim 2 (depends on 1)

The apparatus according to claim 1,
wherein, the second part of the plurality of functions includes at least one of LFNST, LMCS, and ISP.

### Claim 3 (depends on 1)

The apparatus according to claim 1,
wherein, the second part of the plurality of functions includes at least one of Affine, GPM, and MMVD.

### Claim 4 (depends on 1)

The apparatus according to claim 1,
wherein, the second part of the plurality of functions is constrained so as not to be used in generating the encoded data of the frame where the plurality of feature maps is arranged.

### Claim 5 (depends on 1)

The apparatus according to claim 1, wherein, the encoding unit is configured to encode information which indicates that the second part of the plurality of functions is constrained so as not to be used in decoding the encoded data of the frame where the plurality of feature maps is arranged.

### Claim 6 (depends on 1)

The apparatus according to claim 1, wherein the apparatus is for generating first encoded data and second encoded data, and wherein, the first encoded data is compliant with a first coding standard, the second encoded data is compliant with a second coding standard.

### Claim 7 (depends on 1)

The apparatus according to claim 1,
wherein each of the plurality of feature maps is arranged in the frame according to a raster-scan arrangement.

### Claim 8 (depends on 1)

The apparatus according to claim 1, wherein a feature map having a first width and a first height among the plurality of feature maps is arranged in a first area of the frame, and a feature map having a second width smaller than the first width and a second height smaller than the first height among the plurality of feature maps is arranged in a second area of the frame, different from the first area.

### Claim 9 (depends on 1)

The apparatus according to claim 1, wherein the plurality of feature maps is obtained by performing quantization on each of the plurality of feature maps that constitutes a tensor, which is obtained based at least on the processing of a neural network on the input image.

### Claim 10

A decoding apparatus comprising:
a determining unit for determining whether to decode encoded data of a frame where a plurality of feature maps obtained based at least on processing an input image by a neural network is arranged; and
a decoding unit for decoding encoded data of an input image using a plurality of functions including at least deblocking filter in a case where the encoded data of the input image is to be decoded instead of the frame where the plurality of feature maps is arranged,
wherein in a case where it is determined that the encoded data of the frame, where the plurality of feature maps is arranged, is to be decoded, the decoding unit uses a first part of the plurality of functions but does not use a second part of the plurality of functions including the deblocking filter.

### Claim 11 (depends on 10)

The apparatus according to claim 10,
wherein, the second part of the plurality of functions includes at least one of LFNST, LMCS, and ISP.

### Claim 12 (depends on 10)

The apparatus according to claim 10,
wherein, the second part of the plurality of functions includes at least one of Affine, GPM, and MMVD.

### Claim 13 (depends on 10)

The apparatus according to claim 10,
wherein, the second part of the plurality of functions are constrained so as not to be used in decoding the encoded data of the frame where the plurality of the feature maps is arranged.

### Claim 14 (depends on 10)

The apparatus according to claim 10, wherein, the decoding unit is configured to decode information which indicates that the second part of the plurality of functions is constrained so as not to be used in decoding the encoding data of the frame where the plurality of feature maps is arranged.

### Claim 15 (depends on 10)

The method according to claim 10, wherein the apparatus is for generating first encoded data and second encoded data, and wherein, the first encoded data is compliant with a first coding standard, the second encoded data is compliant with a second coding standard.

### Claim 16 (depends on 10)

The apparatus according to claim 10,
wherein each of the plurality of feature maps is arranged in the frame according to a raster-scan arrangement.

### Claim 17 (depends on 10)

The apparatus according to claim 10, wherein a feature map having a first width and a first height among the plurality of feature maps is arranged in a first area of the frame, and a feature map having a second width smaller than the first width and a second height smaller than the first height among the plurality of feature maps is arranged in a second area of the frame, different from the first area.

### Claim 18 (depends on 10)

The apparatus according to claim 10, wherein the plurality of feature maps is obtained by performing quantization on each of the plurality of feature maps that constitutes a tensor, which is obtained based at least on the processing of a neural network on the input image.

### Claim 19

A decoding method comprising:
determining whether to decode encoded data of a frame where a plurality of feature maps obtained based at least on processing an input image by a neural network is arranged; and
decoding encoded data of an input image using a plurality of functions including at least deblocking filter in a case where the encoded data of the input image is to be decoded instead of the frame where the plurality of feature maps is arranged,
wherein in a case where it is determined that the encoded data of the frame, where the plurality of feature maps is arranged, is to be decoded, using a first part of the plurality of functions and not using a second part of the plurality of functions including the deblocking filter.

### Claim 20

A non-transitory computer-readable storage medium which stores a program for executing a method of generating encoded data, the method comprising:
determining whether to generate encoded data of a frame where a plurality of feature maps obtained based at least on processing an input image by a neural network is arranged; and
generating encoded data of an input image using a plurality of functions including at least deblocking filter in a case where the encoded data of the input image is to be generated instead of the frame where the plurality of feature maps is arranged,
wherein in a case where it is determined that the encoded data of the frame, where the plurality of features maps is arranged, is to be generated, using a first part of the plurality of functions and not using a second part of the plurality of functions including the deblocking filter.

### Claim 21

A non-transitory computer-readable storage medium which stores a program for executing a method of decoding encoded data, the method comprising:
determining whether to decode encoded data of a frame where a plurality of feature maps obtained based at least on processing an input image by a neural network is arranged; and
decoding encoded data of an input image using a plurality of functions including at least deblocking filter in a case where the encoded data of the input image is to be decoded instead of the frame where the plurality of feature maps is arranged,
wherein in a case where it is determined that the encoded data of the frame, where the plurality of feature maps is arranged, is to be decoded, using a first part of the plurality of functions and not using a second part of the plurality of functions including the deblocking filter.

### Claim 22

An encoding method comprising:
determining whether to generate encoded data of a frame where a plurality of feature maps obtained based at least on processing an input image by a neural network is arranged; and
generating encoded data of an input image using a plurality of functions including at least deblocking filter in a case where the encoded data of the input image is to be generated instead of the frame where the plurality of feature maps is arranged,
wherein in a case where it is determined that the encoded data of the frame, wherein the plurality of feature maps is arranged, is to be generated, using a first part of the plurality of functions and not using a second part of the plurality of functions including the deblocking filter.
