DVC: An End-to-end Deep Video Compression Framework

TL;DR

This paper introduces DVC, an end-to-end deep learning framework for video compression that jointly optimizes motion estimation, residual encoding, and reconstruction, outperforming traditional standards like H.264 and rivaling H.265.

Contribution

It presents the first fully end-to-end neural network-based video compression model that integrates all components into a single trainable system.

Findings

Outperforms H.264 in PSNR

Comparable to H.265 in MS-SSIM

Joint optimization improves compression efficiency

Abstract

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional video compression method and the powerful non-linear representation ability of neural networks, we propose the first end-to-end video compression deep model that jointly optimizes all the components for video compression. Specifically, learning based optical flow estimation is utilized to obtain the motion information and reconstruct the current frames. Then we employ two auto-encoder style neural networks to compress the corresponding motion and residual information. All the modules are jointly learned through a single loss function, in which they collaborate with each other by considering the trade-off between reducing the number of compression bits and improving quality of the decoded video. Experimental results show that the proposed approach can outperform the widely used video coding standard H.264 in terms of PSNR and be even on par with the latest standard H.265 in terms of MS-SSIM. Code is released at https://github.com/GuoLusjtu/DVC.