A stereo video compression method with dual-branch attention

By employing a dual-branch attention-based stereo video compression method, and utilizing LGEDB and DHFFM modules to extract and fuse local and global features of stereo video, the problem of poor image reconstruction quality in existing technologies is solved, achieving higher quality image reconstruction results.

CN120050431BActive Publication Date: 2026-04-14CHONGQING UNIV OF POSTS & TELECOMM
0 Cites 0 Cited by

Patent Information

Application Number
CN202510229638.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-02-28
Publication Date
2026-04-14
Estimated Expiration
2045-02-28

AI Technical Summary

Technical Problem

Existing stereoscopic video compression methods are insufficient in capturing local non-repeating texture details and global structural information, resulting in poor image reconstruction quality after decoding.

Method used

A stereo video compression method based on bi-branch attention is adopted, which extracts and fuses motion compensation features and disparity compensation features through local and global bi-branch codec blocks (LGEDB) and bi-branch high-frequency information fusion modules (DHFFM), thereby achieving accurate capture and efficient fusion of local non-repeating texture details and global structural information.

Benefits of technology

Higher quality image reconstruction was achieved at the same or lower bit rate, improving the performance of stereoscopic video compression.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a stereo video compression method with double-branch attention, comprising the following steps: dividing a stereo video into a left video frame sequence and a right video frame sequence; inputting a video frame of the stereo video at time t, a time-adjacent reconstructed frame and a view-adjacent reconstructed frame of the video frame into a DAN stereo video compressor to obtain a video reconstructed frame at time t; wherein the DAN stereo video compressor comprises the following modules: a feature extraction module, a motion estimation module, a disparity estimation module, an LGEDB-based coding and decoding module, a motion compensation module, a disparity compensation module, a double-branch high-frequency information fusion module and an image reconstruction module; and the LGEDB and the DHFFM can realize higher-quality image reconstruction with the same or lower Bits Per Pixel (BPP).
Need to check novelty before this filing date? Find Prior Art