提出可逆高效扩散模型，解决图像融合中细节丢失问题。
Reversible Efficient Diffusion for Image Fusion
- 采用可逆架构避免噪声累积，提升融合稳定性
- 显式监督训练，保持生成质量同时减少计算开销
- 适合对细节保留要求高的多模态图像融合任务
多模态图像融合旨在将不同源图像中的互补信息整合为统一表示，期望融合图像既保留精细细节又具备高视觉保真度。尽管扩散模型在图像生成中表现优异，但在图像融合任务中常因马尔可夫过程固有的噪声误差累积导致细节损失，造成结果不一致和退化。而端到端训练中引入显式监督又带来计算效率问题。为此，我们提出可逆高效扩散（RED）模型——一种显式监督训练框架，继承扩散模型强大生成能力的同时，规避了分布估计需求，有效缓解细节丢失问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。