Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compression

TL;DR

This paper presents DiQP, a Transformer-Diffusion model designed to restore 8K videos degraded by codec compression, effectively reversing artifacts without additional noise modeling, and outperforming existing methods in high-resolution video restoration.

Contribution

Introduces the first diffusion-based model that restores codec compression artifacts in high-resolution videos using a Transformer architecture with auxiliary modules.

Findings

Outperforms state-of-the-art video restoration methods.

Effectively restores 8K videos compressed by AV1 and HEVC.

Demonstrates superior visual quality in high-resolution video restoration.

Abstract

In this paper, we introduce DiQP; a novel Transformer-Diffusion model for restoring 8K video quality degraded by codec compression. To the best of our knowledge, our model is the first to consider restoring the artifacts introduced by various codecs (AV1, HEVC) by Denoising Diffusion without considering additional noise. This approach allows us to model the complex, non-Gaussian nature of compression artifacts, effectively learning to reverse the degradation. Our architecture combines the power of Transformers to capture long-range dependencies with an enhanced windowed mechanism that preserves spatiotemporal context within groups of pixels across frames. To further enhance restoration, the model incorporates auxiliary "Look Ahead" and "Look Around" modules, providing both future and surrounding frame information to aid in reconstructing fine details and enhancing overall visual quality. Extensive experiments on different datasets demonstrate that our model outperforms state-of-the-art methods, particularly for high-resolution videos such as 4K and 8K, showcasing its effectiveness in restoring perceptually pleasing videos from highly compressed sources.