# Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference

arXiv: https://arxiv.org/abs/2511.16137 · HTML: https://mlsanity.com/paper/2511.16137/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Cross-Entropy Loss Functions: Theoretical Analysis and Applications](https://mlsanity.com/paper/2304.07288/) (2023)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video](https://mlsanity.com/paper/1902.09707/) (2019)
- [Multi-Frame Quality Enhancement for Compressed Video](https://mlsanity.com/paper/1803.04680/) (2018)
- [A Comprehensive Benchmark for Single Image Compression Artifacts Reduction](https://mlsanity.com/paper/1909.03647/) (2019)
- [Enhancing Quality for HEVC Compressed Videos](https://mlsanity.com/paper/1709.06734/) (2017)
- [Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images](https://mlsanity.com/paper/2006.16581/) (2020)
- [A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding](https://mlsanity.com/paper/1608.06690/) (2016)
- [Non-Local ConvLSTM for Video Compression Artifact Reduction](https://mlsanity.com/paper/1910.12286/) (2019)
- [Adaptive Patch Exiting for Scalable Single Image Super-Resolution](https://mlsanity.com/paper/2203.11589/) (2022)
- [Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction](https://mlsanity.com/paper/2108.02110/) (2021)
- [A DenseNet Based Approach for Multi-Frame In-Loop Filter in HEVC](https://mlsanity.com/paper/1903.01648/) (2019)
- [Partition-Aware Adaptive Switching Neural Networks for Post-Processing in HEVC](https://mlsanity.com/paper/1912.11604/) (2019)
- [End-to-end Transformer for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2210.13827/) (2022)
- [Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure](https://mlsanity.com/paper/1901.09575/) (2019)
- [Transcoded Video Restoration by Temporal Spatial Auxiliary Network](https://mlsanity.com/paper/2112.07948/) (2021)
- [Plug-and-Play Versatile Compressed Video Enhancement](https://mlsanity.com/paper/2504.15380/) (2025)

## Abstract (arXiv)

Existing studies on quality enhancement for compressed video (QECV) predominantly rely on known quantization parameters (QPs), training separate enhancement models for each QP setting, which are referred to as non-blind methods. However, in practical scenarios such as transcoding and transmission, QPs may be partially or entirely unavailable, which limits the applicability of these methods and motivates the development of blind QECV techniques. Existing blind methods typically generate degradation vectors using classification models trained with cross-entropy loss, and employ them as channel attention to guide artifact reduction. Nevertheless, such degradation representations mainly capture global compression information and lack fine-grained spatial cues, making them less effective in handling spatially varying artifact patterns. To address this issue, we propose a pre-trained degradation representation learning module that decouples and extracts high-dimensional, multi-scale degradation representations from compressed video content, providing fine-grained guidance for artifact reduction. Furthermore, most existing blind and nonblind methods adopt a uniform inference architecture for all compression levels, ignoring the distinct computational demands of different QPs. To overcome this limitation, we introduce a sequential inference strategy that adaptively adjusts the number of artifact reduction stages according to the estimated compression level. Extensive experiments show that the proposed method significantly improves enhancement performance. In particular, at QP = 22, it raises PSNR improvement from 0.31 dB to 0.65 dB over the previous state-of-the-art blind method. Meanwhile, with the proposed sequential inference strategy, the average inference time at QP = 22 is reduced by 50% compared with that at QP = 42.