12138-chr / MTAIR
☆13Updated 2 months ago
Alternatives and similar repositories for MTAIR
Users that are interested in MTAIR are comparing it to the libraries listed below
Sorting:
- Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration☆42Updated 10 months ago
- ☆13Updated 7 months ago
- From Heavy Rain Removal to Detail Restoration: A Faster and Better Network☆14Updated last year
- [ECCV 2024] Prompt-based test-time real image dehazing: a novel pipeline☆42Updated 6 months ago
- [ECCV‘24] Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint☆34Updated 6 months ago
- ☆22Updated 9 months ago
- PyTorch implementation for Test-Time Degradation Adaptation for Open-Set Image Restoration (ICML 2024, Spotlight)☆15Updated 10 months ago
- ☆12Updated 9 months ago
- [AAAI24] SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency☆18Updated 10 months ago
- Rethinking Multi-Scale Representations in Deep Deraining Transformer☆32Updated last year
- Offical implementation of Universal Image Restoration Pre-training via Degradation Classification (ICLR2025).☆41Updated 3 months ago
- Joint multi-dimensional dynamic attention and transformer for efficient image restoration☆11Updated 10 months ago
- This is official repository for "LIR: Efficient Degradation Removal for Lightweight Image Restoration"☆9Updated 11 months ago
- [NeurIPS23] PromptRestorer: A Prompting Image Restoration Method with Degradation Perception☆15Updated 9 months ago
- [AAAI 2024] Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration☆35Updated last year
- Here is the code for the TPAMI paper: Advancing Real-World Image Dehazing:Perspective, Modules, and Training.☆22Updated 4 months ago
- The official Pytorch Implementation of AnyIR for All in One Image Restoration☆24Updated 4 months ago
- [NeurIPS2024 Spotlight] Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network☆54Updated last month
- [arXiv 2024] LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration