Research map / Image generation / Image restoration
Discovering Unseen Degradations to Adapt Open-World Image Restoration
Boseong Kim, Tae Hyun Kim, Donghyeon Cho
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a continual image restoration framework that discovers unseen, mixed degradations in open-world settings and adapts a pre-trained all-in-one restorer to them without paired supervision.
Problem
All-in-one image restoration models work in closed-set settings but fail in open-world deployment, where paired supervision is unavailable and degradations are unknown and often intricately mixed.
Approach
Integrates degradation discovery with adaptive restoration in a continual framework, building on a pre-trained all-in-one restoration model so that unseen degradations can be identified and handled without paired data.
Closest papers by meaning
- Retrieve-to-Restore: Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank (CVPR 2026 · similarity 0.90)
- PRISM: Controllable Diffusion for Compound Image Restoration with Scientific Fidelity (ICLR 2026 · similarity 0.90)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · similarity 0.88)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · similarity 0.88)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.88)
- Test-Time Degradation Adaptation for Open-Set Image Restoration (ICML 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
