# Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration

arXiv: https://arxiv.org/abs/2007.11430 · HTML: https://mlsanity.com/paper/2007.11430/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2020.

## Built on by (most cited first, 21 of 21)

- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [TAPE: Task-Agnostic Prior Embedding for Image Restoration](https://mlsanity.com/paper/2203.06074/) (2022)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [SeD: Semantic-Aware Discriminator for Image Super-Resolution](https://mlsanity.com/paper/2402.19387/) (2024)
- [Prompt-based Ingredient-Oriented All-in-One Image Restoration](https://mlsanity.com/paper/2309.03063/) (2023)
- [NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2504.12711/) (2025)
- [HST: Hierarchical Swin Transformer for Compressed Image Super-resolution](https://mlsanity.com/paper/2208.09885/) (2022)
- [PromptCIR: Blind Compressed Image Restoration with Prompt Learning](https://mlsanity.com/paper/2404.17433/) (2024)
- [Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective](https://mlsanity.com/paper/2303.06859/) (2023)
- [Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal](https://mlsanity.com/paper/2407.16957/) (2024)
- [Hybrid Agents for Image Restoration](https://mlsanity.com/paper/2503.10120/) (2025)
- [NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2604.10634/) (2026)
- [Disentangled Feature Representation for Few-shot Image Classification](https://mlsanity.com/paper/2109.12548/) (2021)
- [NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study](https://mlsanity.com/paper/2504.15003/) (2025)
- [Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration](https://mlsanity.com/paper/2504.09377/) (2025)
- [StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessment](https://mlsanity.com/paper/2207.14489/) (2022)
- [A Dive into SAM Prior in Image Restoration](https://mlsanity.com/paper/2305.13620/) (2023)
- [RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment](https://mlsanity.com/paper/2207.06177/) (2022)
- [A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective](https://mlsanity.com/paper/2111.13078/) (2021)
- [Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection](https://mlsanity.com/paper/2505.04888/) (2025)

## Abstract (arXiv)

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization. We also propose a feature aggregation module (FAM) with channel-wise attention to adaptively filter out the distortion representations and aggregate useful content information from different channels for the construction of raw image. The effectiveness of the proposed scheme is verified by visualizing the correlation matrix of features and channel responses of different distortions. Extensive experimental results also prove superior performance of our approach compared with the latest HD-IR schemes.