mlsanityData to 7 Oct 2026

Reversible Efficient Diffusion for Image Fusion

arXiv 2601.20260 ↗First posted 28 Jan 2026cs.CVcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation. The fused image is expected to preserve fine details and maintain high visual fidelity. While diffusion models have demonstrated impressive generative capabilities in image generation, they often suffer from detail loss when applied to image fusion tasks. This issue arises from the accumulation of noise errors inherent in the Markov process, leading to inconsistency and degradation in the fused results. However, incorporating explicit supervision into end-to-end training of diffusion-based image fusion introduces challenges related to computational efficiency. To address these limitations, we propose the Reversible Efficient Diffusion (RED) model - an explicitly supervised training framework that inherits the powerful generative capability of diffusion models while avoiding the distribution estimation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 33 of its 41 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

33 of 41 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model31 Oct
  2. 2023DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion13 Mar
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  8. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 414
  9. 2018Invertible Residual Networkscited by 364
  10. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 313
  11. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  12. 2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 229
18 more
  1. 2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 222
  2. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 215
  3. 2018DenseFuse: A Fusion Approach to Infrared and Visible Imagescited by 180
  4. 2021RFN-Nest: An end-to-end residual fusion network for infrared and visible imagescited by 109
  5. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 87
  6. 2024FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mambacited by 81
  7. 2022Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registrationcited by 80
  8. 2017DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairscited by 77
  9. 2024Task-Customized Mixture of Adapters for General Image Fusioncited by 59
  10. 2020Solving Inverse Problems With Deep Neural Networks -- Robustness Included?cited by 58
  11. 2023Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Latercited by 52
  12. 2024MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusioncited by 35
  13. 2022SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Imagescited by 25
  14. 2024FusionMamba: Efficient Remote Sensing Image Fusion with State Space Modelcited by 21
  15. 2022Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localizationcited by 19
  16. 2024Invertible Diffusion Models for Compressed Sensingcited by 12
  17. 2024Test-Time Dynamic Image Fusioncited by 6
  18. 2022Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attentioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Dig2DIG: Dig into Diffusion Information Gains for Image Fusion
  2. 2025FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching
  3. 2025Efficient Rectified Flow for Image Fusion
  4. 2025Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach
  5. 2026Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
  6. 2024SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
  7. 2024Diffusion Models For Multi-Modal Generative Modeling
  8. 2026UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion