Lune

ICML2025顶会

Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion

Yiming Sun, Xin Li, Pengfei Zhu, Qinghua Hu, Dongwei Ren, Huiying Xu, Xinzhong Zhu

摘要

Multi-modal image fusion aims to integrate complementary information from different modalities to enhance perceptual capabilities in applications such as rescue and security. However, real-world imaging often suffers from degradation issues, such as noise, blur, and haze in visible imaging, as well as stripe noise in infrared imaging, which significantly degrades model performance. To address these challenges, we propose a task-gated multi-expert collaboration network (TG-ECNet) for degraded multi-modal image fusion. The core of our model lies in the task-aware gating and multi-expert collaborative framework, where the task-aware gating operates in two stages: degradation-aware gating dynamically allocates expert groups for restoration based on degradation types, and fusion-aware gating guides feature integration across modalities to balance information retention between fusion and restoration tasks. To achieve this, we design a two-stage training strategy that unifies the learning of restoration and fusion tasks. This strategy resolves the inherent conflict in information processing between the two tasks, enabling all-in-one multi-modal image restoration and fusion. Experimental results demonstrate that TG-ECNet significantly enhances fusion performance under diverse complex degradation conditions and improves robustness in downstream applications. The code is available at https: //github.com/LeeX54946/TG-ECNet.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 4 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image Fusion 引用了 Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection
  • Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion 引用了 Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection
  • PromptIR: Prompting for All-in-One Image Restoration 引用了 All-In-One Image Restoration for Unknown Corruption
  • DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion 引用了 Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection
  • DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion 引用了 Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper4

  1. Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image FusionZengyi Yang, Yu Liu, Juan Cheng, Zhiqin Zhu 等CVPR 2026 · 7 次引用
  2. CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image FusionYiming Sun, Yuan Ruan, Qinghua Hu, Pengfei ZhuAAAI 2026
  3. MMVIP: A Visible-infrared Paired Dataset for Multi-weather Marine VisionYunpeng Yin, Lihan Wang, Zhaoshen He, Xinqiang He 等CVPR 2026
  4. DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object DetectionRui Chen, Dongdong Li, Yan Fan, Yan Liu 等ICML 2026

它引用的 Paper14

  1. Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object DetectionJinyuan Liu, Xin Fan, Zhanbo Huang, Guanyao Wu 等CVPR 2022 · 929 次引用
  2. Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and IntensityHao Zhang, Han Xu, Yang Xiao, Xiaojie Guo 等AAAI 2020 · 583 次引用
  3. PromptIR: Prompting for All-in-One Image RestorationVaishnav Potlapalli, Syed Waqas Zamir, Salman H. Khan, Fahad Shahbaz KhanNeurIPS 2023 · 386 次引用
  4. DDFM: Denoising Diffusion Model for Multi-Modality Image FusionZixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang 等ICCV 2023 · 350 次引用
  5. All-In-One Image Restoration for Unknown CorruptionBoyun Li, Xiao Liu, Peng Hu, Zhongqin Wu 等CVPR 2022 · 338 次引用

相关 Paper

  1. ALLNet: Multi-task Dense Prediction for Degraded ImagesWeiran Wang, Jialing Wu, Yaqi Chang, Gang He 等CVPR 2026
  2. Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image FusionBing Cao, Yiming Sun, Pengfei Zhu, Qinghua HuICCV 2023 · 110 次引用
  3. Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image FusionXunpeng Yi, Han Xu, Hao Zhang, Linfeng Tang 等CVPR 2024 · 121 次引用
  4. MdaIF: Robust One-Stop Multi-Degradation-Aware Image Fusion with Language-Driven SemanticsJing Li, Yifan Wang, Jiafeng Yan, Renlong Zhang 等AAAI 2026
  5. AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationYuning Cui, Syed Waqas Zamir, Salman H. Khan, Alois Knoll 等ICLR 2025 · 9 次引用
黄昏的海面,两侧是细线勾勒的悬崖