Learned Video Compression via Heterogeneous Deformable Compensation Network

TL;DR

This paper introduces a novel learned video compression framework using heterogeneous deformable kernels for motion compensation, significantly improving performance over existing methods.

Contribution

It proposes a content-adaptive heterogeneous deformable kernel approach and a multi-frame reconstruction module, advancing learned video compression techniques.

Findings

Achieves superior compression performance compared to state-of-the-art methods.

Introduces HetDeform kernels for more stable motion compensation.

Employs a multi-frame reconstruction for enhanced quality.

Abstract

Learned video compression has recently emerged as an essential research topic in developing advanced video compression technologies, where motion compensation is considered one of the most challenging issues. In this paper, we propose a learned video compression framework via heterogeneous deformable compensation strategy (HDCVC) to tackle the problems of unstable compression performance caused by single-size deformable kernels in downsampled feature domain. More specifically, instead of utilizing optical flow warping or single-size-kernel deformable alignment, the proposed algorithm extracts features from the two adjacent frames to estimate content-adaptive heterogeneous deformable (HetDeform) kernel offsets. Then we transform the reference features with the HetDeform convolution to accomplish motion compensation. Moreover, we design a Spatial-Neighborhood-Conditioned Divisive Normalization (SNCDN) to achieve more effective data Gaussianization combined with the Generalized Divisive Normalization. Furthermore, we propose a multi-frame enhanced reconstruction module for exploiting context and temporal information for final quality enhancement. Experimental results indicate that HDCVC achieves superior performance than the recent state-of-the-art learned video compression approaches.