通过分离结构与外观实现跨域图像配准，提升医学与遥感图像对齐效果。
SAS-Net: Cross-Domain Image Registration as Inverse Rendering via Structure-Appearance Factorization
- 将图像配准建模为逆渲染问题，分离场景结构与域特有外观。
- 在EuroSAT-Reg-256和FIRE-Reg-256上达到当前最优性能。
- 模型轻量（335万参数），推理速度达89帧/秒，适合实时应用。
跨域图像配准需对齐不同成像物理条件下的图像，经典亮度恒定假设在此失效。本文提出图像生成模型 I = R(s, a) + epsilon，其中观测图像由渲染函数 R 作用于域不变的场景结构 s 与域特定的外观统计量 a 生成。配准转化为逆渲染问题：给定两域观测，恢复共享结构并在目标外观下重渲染以获得配准输出。我们构建SAS-Net（场景-外观分离网络），使用实例归一化实现结构-外观分解，自适应实例归一化（AdaIN）实现可微前向渲染。场景一致性损失在因子化隐空间中强制几何对应。在EuroSAT-Reg-256（卫星遥感）与FIRE-Reg-256（视网膜眼底）数据集上的实验表明，SAS-Net在跨域图像配准任务中表现领先。该模型仅335万参数，在RTX 5090上达到89帧/秒的推理速度。代码已开源：https://github.com/D-ST-Sword/SAS-Net。
原文摘要 · Abstract (English)
Cross-domain image registration requires aligning images acquired under heterogeneous imaging physics, where the classical brightness constancy assumption is fundamentally violated. We formulate this problem through an image formation model I = R(s, a) + epsilon, where each observation is generated by a rendering function R acting on domain-invariant scene structure s and domain-specific appearance statistics a. Registration then reduces to an inverse rendering problem: given observations from two domains, recover the shared structure and re-render it under the target appearance to obtain the registered output. We instantiate this framework as SAS-Net (Scene-Appearance Separation Network), where instance normalization implements the structure-appearance decomposition and Adaptive Instance Normalization (AdaIN) realizes the differentiable forward renderer. A scene consistency loss enforces geometric correspondence in the factorized latent space. Experiments on EuroSAT-Reg-256 (satellite remote sensing) and FIRE-Reg-256 (retinal fundus) demonstrate state-of-the-art performance across heterogeneous imaging domains. SAS-Net (3.35M parameters) achieves 89 FPS on an RTX 5090 GPU. Code: https://github.com/D-ST-Sword/SAS-Net.
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。