Research map / Vision-language and multimodal / Cross-modal learning

MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion

NeurIPS 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion

Read the paperCheck your idea against 108,967 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 MODULE, a mutual-promoting deep unfolding framework for degradation-robust multi-modal image fusion that addresses cascaded sub-optimal solutions and black-box opacity of prior methods.

Problem

Multi-modal image fusion degrades under real-world image degradations, and existing degradation-robust fusion methods rely on cascaded sub-optimal solutions or are black-box.

Approach

A theory-inspired deep unfolding framework in which fusion and degradation-handling components are optimized in a mutually promoting manner, rather than as cascaded stages, yielding an interpretable network.

Experimental setup

Builds on: deep unfolding

Closest papers by meaning

• Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion (ICML 2025 · similarity 0.88)
• ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025 · similarity 0.88)
• Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions (AAAI 2026 · similarity 0.87)
• Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks (CVPR 2025 · similarity 0.87)
• A Closer Look at Multimodal Representation Collapse (ICML 2025 · similarity 0.87)
• Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion (NeurIPS 2026 · similarity 0.86)