End-to-end Neural Video Coding Using a Compound Spatiotemporal Representation

TL;DR

This paper introduces a hybrid neural video coding method that combines vector-based and adaptive kernel-based resampling techniques through a compound spatiotemporal representation, achieving state-of-the-art compression efficiency.

Contribution

It proposes a novel hybrid motion compensation approach with a compound spatiotemporal representation and a multi-prediction decoder, improving robustness and coding efficiency over existing methods.

Findings

Outperforms traditional codecs like H.264 and H.265 in PSNR and MS-SSIM.

Provides better motion prediction and robustness to occlusions.

Achieves state-of-the-art performance in low-delay scenarios.

Abstract

Recent years have witnessed rapid advances in learnt video coding. Most algorithms have solely relied on the vector-based motion representation and resampling (e.g., optical flow based bilinear sampling) for exploiting the inter frame redundancy. In spite of the great success of adaptive kernel-based resampling (e.g., adaptive convolutions and deformable convolutions) in video prediction for uncompressed videos, integrating such approaches with rate-distortion optimization for inter frame coding has been less successful. Recognizing that each resampling solution offers unique advantages in regions with different motion and texture characteristics, we propose a hybrid motion compensation (HMC) method that adaptively combines the predictions generated by these two approaches. Specifically, we generate a compound spatiotemporal representation (CSTR) through a recurrent information aggregation (RIA) module using information from the current and multiple past frames. We further design a one-to-many decoder pipeline to generate multiple predictions from the CSTR, including vector-based resampling, adaptive kernel-based resampling, compensation mode selection maps and texture enhancements, and combines them adaptively to achieve more accurate inter prediction. Experiments show that our proposed inter coding system can provide better motion-compensated prediction and is more robust to occlusions and complex motions. Together with jointly trained intra coder and residual coder, the overall learnt hybrid coder yields the state-of-the-art coding efficiency in low-delay scenario, compared to the traditional H.264/AVC and H.265/HEVC, as well as recently published learning-based methods, in terms of both PSNR and MS-SSIM metrics.