TL;DR
The paper introduces DACG-IR, a novel degradation-aware model for unified image restoration that dynamically modulates features based on degradation characteristics, outperforming existing methods.
Contribution
It proposes a degradation-aware adaptive gating mechanism with a multi-scale module and dual-gated fusion for improved image restoration across diverse degradations.
Findings
DACG-IR outperforms state-of-the-art methods in various restoration tasks.
The model effectively suppresses noise and preserves structures.
It handles multiple degradation types with a single model.
Abstract
Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Gating), which enables explicit perception of degradation characteristics to dynamically modulate feature representations. Our method constructs degradation-aware contextual representations from the input to modulate attention distribution, frequency-domain features, and feature aggregation. Specifically, a lightweight multi-scale degradation-aware module extracts coarse degradation information and generates layer-wise prompts. These prompts guide attention temperature and output gating in encoder and decoder blocks for adaptive feature extraction. Additionally, a spatial-channel dual-gated adaptive fusion mechanism refines encoder features, suppressing noise propagation from shallow to deep layers. This design…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
