maouestc/SPME

Han Gao, JINZHONG CUI, Mao Ye, Shuai Li, Yu Zhao, Xiatian Zhu, Structure-Preserving Motion Estimation for Learned Video Compression, ACM Multimedia 2022

Structure-Preserving Motion Estimation for Learned Video Compression

This is the official implementation and appendix of the paper:

Structure-Preserving Motion Estimation for Learned Video Compression. Han Gao, Jinzhong Cui, Mao Ye, Shuai Li, Yu Zhao, Xiatian Zhu. ACM Multimedia 2022. [Link(TODO)]

TODO

• Upload appendix.pdf;
• Upload codes;
• Upload pretrained models;
• Update README.md.

Overview

Requirements

• Python==3.8
• Pytorch==1.9

Data Preparation

Training dataset

• Download Vimeo-90k dataset.

Testing dataset

• Download HEVC dataset, UVG dataset(1080p/8bit/YUV/RAW) and MCL-JCV dataset.

Run

Acknowledgement

During implementation, we drawed on the experience of CompressAI, PyTorchVideoCompression and DCVC. The model weights of intra coding are from CompressAI.

Citation

If you find this paper useful, kindly cite:

Contact

If any questions, kindly contact with Han Gao via e-mail: han.gao@std.uestc.edu.cn.