UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy
- LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration
- An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training
- Efficient Degradation-aware Any Image Restoration
- Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation
- A Preliminary Exploration Towards General Image Restoration
- HQ-50K: A Large-scale, High-quality Dataset for Image Restoration
- Exploring Scalable Unified Modeling for General Low-Level Vision
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