发表机构
Technical University of Munich; Munich Center for Machine Learning（慕尼黑工业大学; 慕尼黑机器学习中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
UltraDiff将可微渲染扩展到超声，通过路径空间积分与蒙特卡洛估计实现梯度优化，在无监督B-mode图像上恢复椎体表面，达到竞争性几何精度。
AI 中文摘要
基于物理的可微渲染通过将渲染图像与测量值匹配，实现了场景参数的梯度优化，但迄今为止主要聚焦于光传输。我们将这一范式扩展到医学超声领域，在该领域中，图像形成类似于瞬态渲染：回波按飞行时间分箱，而非投影到图像平面上。我们提出了UltraDiff，一个用于可微超声光线追踪的模块化框架。UltraDiff将超声图像形成表述为路径空间积分，由换能器与组织界面之间的传播时间进行门控，并推导出前向模型及其相对于场景参数梯度的蒙特卡洛估计器。我们通过一个逆几何估计问题对此进行了演示：从一个球体出发，优化一个SDF（符号距离函数），直到模拟回波与测量回波匹配，从而从模拟的B-mode扫描以及真实机器人采集的脊柱体模中恢复椎体表面。与依赖于预分割图像的最先进的超声形状重建方法不同，我们的方法通过分析-合成方式在B-mode图像上进行无监督操作，同时实现了具有竞争力的几何精度。UltraDiff基于Mitsuba 3实现，将可微路径追踪引入了一种新的传感模态，并为声学成像中的逆问题提供了基础。
英文摘要
Physically-based differentiable rendering enables gradient-based optimization of scene parameters by matching rendered images to measurements, but has so far mainly focused on light transport. We extend this paradigm to medical ultrasound, where image formation resembles transient rendering: echoes are binned by time-of-flight rather than projected onto an image plane. We present UltraDiff, a modular framework for differentiable ultrasound ray tracing. UltraDiff formulates ultrasound image formation as a path-space integral, gated by travel time between the transducer and tissue interfaces, and derives a Monte Carlo estimator of both the forward model and its gradients with respect to scene parameters. We demonstrate this on an inverse geometry estimation: starting from a sphere, an SDF is optimized until simulated echoes match measured ones, recovering vertebral surfaces from simulated B-mode sweeps and from a real robotic acquisition of a spine phantom. Unlike state-of-the-art ultrasound shape reconstruction methods, which rely on pre-segmented images, our approach operates unsupervised on B-mode images through analysis-by-synthesis, while achieving competitive geometric accuracy. Implemented on top of Mitsuba 3, UltraDiff brings differentiable path tracing to a new sensing modality and provides a foundation for inverse problems in acoustic imaging.
Comments4 pages, 4 figures, 1 table. Accepted at SIGGRAPH Asia 2026 Technical Communications
