What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 6128-6137
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (NSFC) (62306064)
- Sichuan Science and Technology Program (No. 2024ZDZX0011)
- Sichuan Science and Technology Program (No. 2026NSFSC1482)
- Sichuan Science and Technology Program (No. 2025ZHCG0002)
This publication has 19 references indexed in Scilit:
- Complexity Experts are Task-Discriminative Learners for Any Image Restoration2025
- SRMamba-T: Exploring the hybrid Mamba-Transformer network for Single Image Super-ResolutionNeurocomputing, 2025
- Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration2024
- Language-driven All-in-one Adverse Weather Removal2024
- Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model2024
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Deep Joint Rain Detection and Removal from a Single Image2017
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2017
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002