Universal Image Restoration Pre-training via Masked Degradation Classification
Abstract
A Masked Degradation Classification Pre-Training method enhances image restoration by using degradation type classification and image reconstruction, improving performance across CNNs and Transformers.
This study introduces a Masked Degradation Classification Pre-Training method (MaskDCPT), designed to facilitate the classification of degradation types in input images, leading to comprehensive image restoration pre-training. Unlike conventional pre-training methods, MaskDCPT uses the degradation type of the image as an extremely weak supervision, while simultaneously leveraging the image reconstruction to enhance performance and robustness. MaskDCPT includes an encoder and two decoders: the encoder extracts features from the masked low-quality input image. The classification decoder uses these features to identify the degradation type, whereas the reconstruction decoder aims to reconstruct a corresponding high-quality image. This design allows the pre-training to benefit from both masked image modeling and contrastive learning, resulting in a generalized representation suited for restoration tasks. Benefit from the straightforward yet potent MaskDCPT, the pre-trained encoder can be used to address universal image restoration and achieve outstanding performance. Implementing MaskDCPT significantly improves performance for both convolution neural networks (CNNs) and Transformers, with a minimum increase in PSNR of 3.77 dB in the 5D all-in-one restoration task and a 34.8% reduction in PIQE compared to baseline in real-world degradation scenarios. It also emergences strong generalization to previously unseen degradation types and levels. In addition, we curate and release the UIR-2.5M dataset, which includes 2.5 million paired restoration samples across 19 degradation types and over 200 degradation levels, incorporating both synthetic and real-world data. The dataset, source code, and models are available at https://github.com/MILab-PKU/MaskDCPT.
Community
We are excited to announce the release of the leading unified image restoration method, MaskDCPT.
- 32.09 dB on 5D all-in-one image restoration, surpasses existing SOTA method by 1.51 dB;
- able to solve mixed and real-world degradation;
- the largest universal image restoration dataset, including 2.5M image pairs and 19 degradation types;
- emerges the ability to generalize to unknown degradation levels.
The code and pretrained models are released at this link.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration (2025)
- Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding (2025)
- A Unified Low-level Foundation Model for Enhancing Pathology Image Quality (2025)
- BIR-Adapter: A Low-Complexity Diffusion Model Adapter for Blind Image Restoration (2025)
- AIM 2025 Challenge on Real-World RAW Image Denoising (2025)
- Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper