# US 12,217,391 B2 · Spatially adaptive image filtering

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

- Number: US 12,217,391 B2
- Document ID: US12217391B2
- Status: Granted
- Kind: B2
- Application number: 17/742,703
- Filed: 2022-05-12
- Published: 2022-09-01
- Granted: 2025-02-04
- Earliest claimed: 2019-11-14
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Filippos Kokkinos; Ioannis Marras; Matteo Maggioni; Stefanos Zafeiriou; Gregory Slabaugh
- Web page: https://patentgrep.com/patent/US12217391B2

## CPC

- G06T 5/20: using local operators
- G06T 5/60: using machine learning, e.g. neural networks
- G06V 10/451: {with interaction between the filter responses, e.g. cortical complex cells}
- G06V 10/82: using neural networks
- G06T 2207/10004: Still image; Photographic image
- G06T 2207/20004: Adaptive image processing
- G06T 2207/20008: Globally adaptive
- G06T 2207/20012: Locally adaptive
- G06T 2207/20024: Filtering details
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20192: Edge enhancement; Edge preservation
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An image processor for transforming an input image, the image processor being configured to implement a trained artificial intelligence model, where the image processor is configured to: receive the input image; based on one or both of (i) the content of the input image and (ii) features extracted from the input image, process the image by the trained artificial intelligence model to: (i) determine a set of image filters; and (ii) for each of a plurality of subregions of the image, select an image filter from the set of image filters; and for each of the plurality of subregions of the image, apply the respective image filter to the subregion or to features extracted from that subregion. This may allow for differentiable selection of filters from a discrete learnable and decorrelated group of filters to allow for content based spatial adaptations.

## Claims

### Claim 1

An image processor for transforming an input image, the image processor being configured to implement a trained artificial intelligence model, wherein the image processor is configured to:
receive the input image;
based on one or both of (i) the content of the input image and (ii) features extracted from the input image, process the image by the trained artificial intelligence model to:
(i) determine a set of image filters; and
(ii) for each of a plurality of subregions of the image, select an image filter from the set of image filters; and
for each of the plurality of subregions of the image, apply the respective image filter to the subregion or to features extracted from that subregion;
wherein the trained artificial intelligence model is a convolutional neural network comprising a regularizer which enforces variability to a learned set of image filters.

### Claim 2 (depends on 1)

The image processor of claim 1, wherein each of the plurality of subregions is a pixel of the input image.

### Claim 3 (depends on 1)

The image processor of claim 1, wherein, for each of the plurality of subregions of the image, the selected image filter is applied to the features extracted from that subregion, and wherein the features extracted from the subregion of the input image are defined in the form of a tensor.

### Claim 4 (depends on 1)

The image processor as claimed in claim 1, wherein the image processor is further configured to, for each of the plurality of subregions of the image, select an image filter from the set of image filters based on one or both of (i) the content of the respective subregion of the image and (ii) features extracted from the respective subregion of the image.

### Claim 5 (depends on 1)

The image processor as claimed in claim 1, wherein the image processor is further configured to, for each of the plurality of subregions of the image, select an image filter from the set of image filters based on one or both of (i) the content of an area around the respective subregion of the image and (ii) features extracted from the areas around the respective subregion of the image.

### Claim 6 (depends on 1)

The image processor as claimed in claim 1, wherein the set of image filters comprises a pre-defined number of discrete filters.

### Claim 7 (depends on 1)

The image processor as claimed in claim 1, wherein each image filter of the set of image filters is unique from the other members of the set.

### Claim 8 (depends on 1)

The image processor as claimed in claim 1, wherein each image filter of the set of image filters is a kernel.

### Claim 9 (depends on 8)

The image processor as claimed in claim 8, wherein the set of image filters comprises kernels having at least two different sizes.

### Claim 10 (depends on 1)

The image processor as claimed in claim 1, wherein the image processor is configured to perform one or more of the following image operations: demosaicking, superresolution, semantic segmentation, and image classification.

### Claim 11

A method for implementation at an image processor for transforming an input image, the image processor being configured to implement a trained artificial intelligence model, the method comprising:
receiving an input image;
based on one or both of (i) the content of the input image and (ii) features extracted from the input image, processing the image by a trained artificial intelligence model to:
(i) determine a set of image filters; and
(ii) for each of a plurality of subregions of the image, select an image filter from the set of image filters; and
for each of the plurality of subregions of the image, applying the respective image filter to the subregion or to features extracted from that subregion;
wherein the trained artificial intelligence model is a convolutional neural network comprising a regularizer which enforces variability to a learned set of image filters.

### Claim 12 (depends on 11)

The method for implementation at an image processor for transforming an input image of claim 11, wherein each of the plurality of subregions is a pixel of the input image.

### Claim 13 (depends on 11)

The method for implementation at an image processor for transforming an input image of claim 11, wherein the set of image filters comprises a pre-defined number of discrete filters.
