TaskIR: Task-Driven Image Restoration via Degradation Adaptation and Task Feedback

arXiv:2609.31170 · cs.CV · Submitted 2026-09-25 · Read on arXiv

cs.CV

Submitted: 2026-09-25

Updated: 2026-09-29

Terminology

• Adaptation — 17× in this paper · explained in 1 episode
• All-in-One Image Restoration — 10× in this paper
• Transformer — 9× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 7× in this paper
• Downstream Tasks — 6× in this paper · explained in 2 episodes
• Selective Task Feedback Refinement — 5× in this paper
• Ablation Studies — 4× in this paper · explained in 1 episode
• Degradation-Guided Transformer Block — 4× in this paper
• Ablation study — 3× in this paper · explained in 1 episode
• Aggregation — 3× in this paper · explained in 1 episode
• Conditional Restoration Refinement — 3× in this paper
• Degradation Representation Module — 3× in this paper
• CVF International Conference on Computer Vision — 2× in this paper
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Multi-scale Degradation Extraction — 2× in this paper
• Regularization — 2× in this paper · explained in 3 episodes
• Task-Related Feedback — 2× in this paper
• Two-stage training — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Closed-Loop Optimization — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Degradation-conditioned Parameter Generator — 1× in this paper
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fourteenth International Conference on Learning Representations — 1× in this paper
• GAP and Global Standard Deviation Pooling — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Task Gap Predictor — 1× in this paper
• Two-Stage Training Strategy — 1× in this paper · explained in 3 episodes

Sources

• HNDiff: Haze-Noise Diffusion for Image Dehazing
• TaskTok: Delving into Task Tokens for Task-driven Image Restoration
• Decoupled Weight Decay Regularization
• TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration
• Deep Retinex Decomposition for Low-Light Enhancement
• Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
• Multi-Scale Context Aggregation by Dilated Convolutions

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models