# Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure

## TL;DR

This paper introduces a novel quality enhancement network for VVC compressed videos that leverages both spatial details and temporal structure to improve visual quality.

## Contribution

It proposes a joint network architecture with dedicated subnets for temporal motion compensation and spatial artifact reduction, advancing video quality enhancement techniques.

## Key findings

- Significant improvement in reconstructed video quality
- Effective reduction of compression artifacts
- Enhanced temporal consistency

## Abstract

In this paper, we propose a quality enhancement network of versatile video coding (VVC) compressed videos by jointly exploiting spatial details and temporal structure (SDTS). The proposed network consists of a temporal structure fusion subnet and a spatial detail enhancement subnet. The former subnet is used to estimate and compensate the temporal motion across frames, and the latter subnet is used to reduce the compression artifacts and enhance the reconstruction quality of compressed video. Experimental results demonstrate the effectiveness of our SDTS-based method.