SASFormer: Stage-Aware Selective Attention Transformer for All-in-One Blind Image Restoration
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/TxpHome/SASFormer
Terminology
Sources
- Degradation-Aware Adaptive Context Gating for Unified Image Restoration
- Prompt-In-Prompt Learning for Universal Image Restoration
- Deep Retinex Decomposition for Low-Light Enhancement
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs