Sorry, you need to enable JavaScript to visit this website.

An Improved Multi-reference Frame Loop Filter Algorithm Based on Transformer for VVC

Citation Author(s):
Zhi Liu, Yunpeng Duan, Mengmeng Zhang
Submitted by:
Yunpeng Duan
Last updated:
2 March 2022 - 6:25am
Document Type:
Poster
Document Year:
2022
Event:
Presenters:
Yunpeng Duan
Paper Code:
144
Categories:
 

Deep learning methods have been achieving good results at the in-loop filtering stage in Versatile Video Coding(VVC). The Multi-Frame In-Loop Filter of HEVC (MIF) algorithm is one of the networks that effectively utilizes the multiple reference frames to enhance the quality of reconstruction. However, it has the disadvantages of low efficiency of the reference frame selection, and its quality enhancement network does not fully utilize the inter-frame correlations of the video sequence and has large redundancy. To address these problems, an improved multi-reference frame loop filter algorithm based on transformer optimization (T-MIF) is proposed.

up
0 users have voted: