# Compression-Realized Deep Structural Network for Video Quality Enhancement

arXiv: https://arxiv.org/abs/2405.06342 · HTML: https://mlsanity.com/paper/2405.06342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 10 May 2024.

## Builds on (most cited first, 30 of 34)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond](https://mlsanity.com/paper/2012.02181/) (2020)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Neighborhood Attention Transformer](https://mlsanity.com/paper/2204.07143/) (2022)
- [TDAN: Temporally Deformable Alignment Network for Video Super-Resolution](https://mlsanity.com/paper/1812.02898/) (2018)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Recurrent Back-Projection Network for Video Super-Resolution](https://mlsanity.com/paper/1903.10128/) (2019)
- [Video Frame Interpolation Transformer](https://mlsanity.com/paper/2111.13817/) (2021)
- [Understanding Deformable Alignment in Video Super-Resolution](https://mlsanity.com/paper/2009.07265/) (2020)
- [MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video](https://mlsanity.com/paper/1902.09707/) (2019)
- [Enhancing Quality for HEVC Compressed Videos](https://mlsanity.com/paper/1709.06734/) (2017)
- [NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results](https://mlsanity.com/paper/2204.09314/) (2022)
- [AccFlow: Backward Accumulation for Long-Range Optical Flow](https://mlsanity.com/paper/2308.13133/) (2023)
- [Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference](https://mlsanity.com/paper/2008.10710/) (2020)
- [Learning for Unconstrained Space-Time Video Super-Resolution](https://mlsanity.com/paper/2102.13011/) (2021)
- [CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2403.10362/) (2024)

## Abstract (arXiv)

This paper focuses on the task of quality enhancement for compressed videos. Although deep network-based video restorers achieve impressive progress, most of the existing methods lack a structured design to optimally leverage the priors within compression codecs. Since the quality degradation of the video is primarily induced by the compression algorithm, a new paradigm is urgently needed for a more ``conscious'' process of quality enhancement. As a result, we propose the Compression-Realized Deep Structural Network (CRDS), introducing three inductive biases aligned with the three primary processes in the classic compression codec, merging the strengths of classical encoder architecture with deep network capabilities. Inspired by the residual extraction and domain transformation process in the codec, a pre-trained Latent Degradation Residual Auto-Encoder is proposed to transform video frames into a latent feature space, and the mutual neighborhood attention mechanism is integrated for precise motion estimation and residual extraction. Furthermore, drawing inspiration from the quantization noise distribution of the codec, CRDS proposes a novel Progressive Denoising framework with intermediate supervision that decomposes the quality enhancement into a series of simpler denoising sub-tasks. Experimental results on datasets like LDV 2.0 and MFQE 2.0 indicate our approach surpasses state-of-the-art models.