# Universal Image Restoration Pre-training via Degradation Classification

arXiv: https://arxiv.org/abs/2501.15510 · HTML: https://mlsanity.com/paper/2501.15510/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2025.

## Built on by (most cited first, 30 of 35)

- [Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images](https://mlsanity.com/paper/2511.07222/) (2025)
- [RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration](https://mlsanity.com/paper/2505.18047/) (2025)
- [IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models](https://mlsanity.com/paper/2505.24406/) (2025)
- [Auto-Regressively Generating Multi-View Consistent Images](https://mlsanity.com/paper/2506.18527/) (2025)
- [Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization](https://mlsanity.com/paper/2505.18679/) (2025)
- [Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context](https://mlsanity.com/paper/2602.21929/) (2026)
- [Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration](https://mlsanity.com/paper/2603.01725/) (2026)
- [Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration](https://mlsanity.com/paper/2504.09973/) (2025)
- [Enhancing Image Restoration Transformer via Adaptive Translation Equivariance](https://mlsanity.com/paper/2506.18520/) (2025)
- [Learning Where and What to Restore for Composite Image Restoration](https://mlsanity.com/paper/2503.17915/) (2025)
- [Universal Image Restoration Pre-training via Masked Degradation Classification](https://mlsanity.com/paper/2510.13282/) (2025)
- [Vision-Language Model Guided Image Restoration](https://mlsanity.com/paper/2512.17292/) (2025)
- [TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration](https://mlsanity.com/paper/2601.20306/) (2026)
- [Towards Unified Image Deblurring using a Mixture-of-Experts Decoder](https://mlsanity.com/paper/2508.06228/) (2025)
- [UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing](https://mlsanity.com/paper/2601.06909/) (2026)
- [Reconstruct Anything Model: a lightweight general model for computational imaging](https://mlsanity.com/paper/2503.08915/) (2025)
- [Clear Nights Ahead: Towards Multi-Weather Nighttime Image Restoration](https://mlsanity.com/paper/2505.16479/) (2025)
- [Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation](https://mlsanity.com/paper/2504.14249/) (2025)
- [RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration](https://mlsanity.com/paper/2509.12039/) (2025)
- [Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors](https://mlsanity.com/paper/2511.17126/) (2025)
- [Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement](https://mlsanity.com/paper/2604.22886/) (2026)
- [Diffusion Once and Done: Degradation-Aware LoRA for Efficient All-in-One Image Restoration](https://mlsanity.com/paper/2508.03373/) (2025)
- [Bridging Degradation Discrimination and Generation for Universal Image Restoration](https://mlsanity.com/paper/2602.00579/) (2026)
- [Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement](https://mlsanity.com/paper/2602.18752/) (2026)
- [Your Pre-trained Diffusion Model Secretly Knows Restoration](https://mlsanity.com/paper/2604.04924/) (2026)
- [Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark](https://mlsanity.com/paper/2604.09313/) (2026)
- [Degradation Frequency Curve: An Explicit Frequency-Quantified Representation for All-in-One Image Restoration](https://mlsanity.com/paper/2605.17506/) (2026)
- [DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration](https://mlsanity.com/paper/2606.19097/) (2026)
- [FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather](https://mlsanity.com/paper/2606.30471/) (2026)
- [CURE: Controllable Unified Image Restoration for Complex Degradations](https://mlsanity.com/paper/2607.03044/) (2026)

## Abstract (arXiv)

This paper proposes the Degradation Classification Pre-Training (DCPT), which enables models to learn how to classify the degradation type of input images for universal image restoration pre-training. Unlike the existing self-supervised pre-training methods, DCPT utilizes the degradation type of the input image as an extremely weak supervision, which can be effortlessly obtained, even intrinsic in all image restoration datasets. DCPT comprises two primary stages. Initially, image features are extracted from the encoder. Subsequently, a lightweight decoder, such as ResNet18, is leveraged to classify the degradation type of the input image solely based on the features extracted in the first stage, without utilizing the input image. The encoder is pre-trained with a straightforward yet potent DCPT, which is used to address universal image restoration and achieve outstanding performance. Following DCPT, both convolutional neural networks (CNNs) and transformers demonstrate performance improvements, with gains of up to 2.55 dB in the 10D all-in-one restoration task and 6.53 dB in the mixed degradation scenarios. Moreover, previous self-supervised pretraining methods, such as masked image modeling, discard the decoder after pre-training, while our DCPT utilizes the pre-trained parameters more effectively. This superiority arises from the degradation classifier acquired during DCPT, which facilitates transfer learning between models of identical architecture trained on diverse degradation types. Source code and models are available at https://github.com/MILab-PKU/dcpt.