# US 2025/0168387 A1 · Content adaptive deblocking during video encoding and decoding

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

- Number: US 2025/0168387 A1
- Document ID: US20250168387A1
- Status: Published application
- Kind: A1
- Application number: 19/025,888
- Filed: 2025-01-16
- Published: 2025-05-22
- Earliest claimed: 2010-10-05
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Xiaoyan Sun; Zhiwei Xiong; Feng Wu
- Web page: https://patentgrep.com/patent/US20250168387A1

## CPC

- H04N 19/51: Motion estimation or motion compensation
- H04N 19/117: Filters, e.g. for pre-processing or post-processing (sub-band filter banks H04N19/635)
- H04N 19/14: Coding unit complexity, e.g. amount of activity or edge presence estimation (H04N19/146 takes precedence)
- H04N 19/176: the region being a block, e.g. a macroblock
- H04N 19/80: Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation (H04N19/635, H04N19/86 take precedence)
- H04N 19/86: involving reduction of coding artifacts, e.g. of blockiness
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Disclosed herein are exemplary embodiments of methods, apparatus, and systems for performing content-adaptive deblocking to improve the visual quality of video images compressed using block-based motion-predictive video coding. For instance, in certain embodiments of the disclosed technology, edge information is obtained using global orientation energy edge detection (“OEED”) techniques on an initially deblocked image. OEED detection can provide a robust partition of local directional features (“LDFs”). For a local directional feature detected in the partition, a directional deblocking filter having an orientation corresponding to the orientation of the LDF can be used. The selected filter can have a filter orientation and activation thresholds that better preserve image details while reducing blocking artifacts. In certain embodiments, for a consecutive non-LDF region, extra smoothing can be imposed to suppress the visually severe blocking artifacts.

## Claims

### Claim 1

(canceled)

### Claim 2

A computer system comprising one or more processing units and memory, wherein the computer system implements a video decoder configured to perform operations comprising:
receiving encoded data for a video frame;
reconstructing, using the encoded data, the video frame;
applying a deblocking filter to at least one component of the reconstructed video frame, including applying the deblocking filter to luminance values of the reconstructed video frame, thereby producing a deblocked, reconstructed video frame; and
based at least in part on a flag, in the encoded data, for part of the video frame:
for a block in the deblocked, reconstructed video frame, determining edge locations throughout the block based at least in part on analysis of pixel values of the block in the deblocked, reconstructed video frame;
selecting a filter from two or more candidate filters associated with different edge orientations, the two or more candidate filters including a candidate filter associated with a horizontal edge orientation, a candidate filter associated with a vertical edge orientation, and multiple candidate filters associated with different diagonal edge orientations; and
selectively applying the selected filter to the block.

### Claim 3 (depends on 2)

The computer system of claim 2, wherein the reconstructing, the applying the deblocking filter, the determining, the selecting, and the selectively applying the selected filter are performed in a motion compensation loop of the video decoder.

### Claim 4 (depends on 2)

The computer system of claim 2, wherein the selectively applying the selected filter includes evaluating one or more application thresholds such that the selected filter is applied at the edge locations determined based at least in part on the analysis of pixel values of the block.

### Claim 5 (depends on 2)

The computer system of claim 2, further comprising repeating the determining, the selecting, and the selectively applying the selected filter for each of one or more other blocks.

### Claim 6 (depends on 2)

The computer system of claim 2, wherein the multiple candidate filters associated with different diagonal edge orientations include:
a candidate filter associated with a 45 degree edge orientation; and
a candidate filter associated with a 135 degree edge orientation.

### Claim 7 (depends on 2)

The computer system of claim 2, wherein at least one of the two or more candidate filters is a smoothing filter configured to remove discontinuity artifacts while preserving real edges.

### Claim 8 (depends on 7)

The computer system of claim 7, wherein the smoothing filter is configured to remove discontinuity artifacts while preserving real edges.

### Claim 9 (depends on 2)

The computer system of claim 2, wherein the selectively applying the selected filter includes evaluating, using the edge locations determined based at least in part on the analysis of pixel values of the block, whether or not to apply the selected filter.

### Claim 10

One or more non-transitory computer-readable media having stored thereon encoded data for a video frame, the encoded data being organized to facilitate decoding, using a computer-implemented video decoder, with operations comprising:
reconstructing, using the encoded data, the video frame;
applying a deblocking filter to at least one component of the reconstructed video frame, including applying the deblocking filter to luminance values of the reconstructed video frame, thereby producing a deblocked, reconstructed video frame; and
based at least in part on a flag, in the encoded data, for part of the video frame:
for a block in the deblocked, reconstructed video frame, determining edge locations throughout the block based at least in part on analysis of pixel values of the block in the deblocked, reconstructed video frame;
selecting a filter from two or more candidate filters associated with different edge orientations, the two or more candidate filters including a candidate filter associated with a horizontal edge orientation, a candidate filter associated with a vertical edge orientation, and multiple candidate filters associated with different diagonal edge orientations; and
selectively applying the selected filter to the block.

### Claim 11 (depends on 10)

The one or more non-transitory computer-readable media of claim 10, wherein the selectively applying the selected filter includes evaluating one or more application thresholds such that the selected filter is applied at the edge locations determined based at least in part on the analysis of pixel values of the block.

### Claim 12 (depends on 10)

The one or more non-transitory computer-readable media of claim 10, wherein the multiple candidate filters associated with different diagonal edge orientations include:
a candidate filter associated with a 45 degree edge orientation; and
a candidate filter associated with a 135 degree edge orientation.

### Claim 13 (depends on 10)

The one or more non-transitory computer-readable media of claim 10, wherein at least one of the two or more candidate filters is a smoothing filter configured to remove discontinuity artifacts while preserving real edges.

### Claim 14 (depends on 10)

The one or more non-transitory computer-readable media of claim 10, wherein the selectively applying the selected filter includes evaluating, using the edge locations determined based at least in part on the analysis of pixel values of the block, whether or not to apply the selected filter.

### Claim 15

A computer system comprising one or more processing units and memory, wherein the computer system implements a video encoder configured to perform operations comprising:
encoding a video frame, thereby producing encoded data for the video frame;
outputting the encoded data for the video frame, the encoded data including a flag for part of the video frame;
reconstructing the video frame;
applying a deblocking filter to at least one component of the reconstructed video frame, including applying the deblocking filter to luminance values of the reconstructed video frame, thereby producing a deblocked, reconstructed video frame; and
in accordance with the flag, in the encoded data, for the part of the video frame:
for a block in the deblocked, reconstructed video frame, determining edge locations throughout the block based at least in part on analysis of pixel values of the block in the deblocked, reconstructed video frame;
selecting a filter from two or more candidate filters associated with different edge orientations, the two or more candidate filters including a candidate filter associated with a horizontal edge orientation, a candidate filter associated with a vertical edge orientation, and multiple candidate filters associated with different diagonal edge orientations; and
selectively applying the selected filter to the block.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein the reconstructing, the applying the deblocking filter, the determining, the selecting, and the selectively applying the selected filter are performed in a motion compensation loop of the video encoder.

### Claim 17 (depends on 15)

The computer system of claim 15, wherein the operations further comprise repeating the determining, the selecting, and the selectively applying the selected filter for each of one or more other blocks.

### Claim 18 (depends on 15)

The computer system of claim 15, wherein the multiple candidate filters associated with different diagonal edge orientations include:
a candidate filter associated with a 45 degree edge orientation; and
a candidate filter associated with a 135 degree edge orientation.

### Claim 19 (depends on 15)

The computer system of claim 15, wherein at least one of the two or more candidate filters is a smoothing filter.

### Claim 20 (depends on 19)

The computer system of claim 19, wherein the smoothing filter is configured to remove discontinuity artifacts while preserving real edges.

### Claim 21 (depends on 15)

The computer system of claim 15, wherein the selectively applying the selected filter includes evaluating, using the edge locations determined based at least in part on the analysis of pixel values of the block, whether or not to apply the selected filter.
