Reversible Efficient Diffusion for Image Fusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912854281551872 |
|---|---|
| author | Xu, Xingxin Cao, Bing Li, DongDong Hu, Qinghua Zhu, Pengfei |
| author_facet | Xu, Xingxin Cao, Bing Li, DongDong Hu, Qinghua Zhu, Pengfei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20260 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reversible Efficient Diffusion for Image Fusion Xu, Xingxin Cao, Bing Li, DongDong Hu, Qinghua Zhu, Pengfei Computer Vision and Pattern Recognition 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. |
| title | Reversible Efficient Diffusion for Image Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.20260 |