arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.02866cs.LGcs.NAmath.NA
收藏

反投影扩散:利用扩散模型求解宽带逆散射问题

Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models

Department of Mathematics University of Wisconsin-Madison(数学系 威斯康星大学麦迪逊分校);Google Research(谷歌研究)

Borong Zhang, Martín Guerra, Qin Li, Leonardo Zepeda-Núñez

AI总结:

本研究提出宽带反投影扩散端到端概率框架,通过两步法结合物理对称性与条件扩散模型求解宽带逆散射问题,实现高精度、低复杂度的重建,可恢复亚奈奎斯特特征。

摘要:

我们提出了宽带反投影扩散(Wideband Back-Projection Diffusion),这是一种端到端概率框架,用于逼近由宽带散射数据的逆散射映射所诱导的后验分布。该框架利用条件扩散模型生成样本,可实现高精度重建,同时遵循波传播基础物理的对称性。整个流程分为两个步骤:第一步受滤波反投影公式启发,将数据转换为基于物理的潜表示;第二步学习以该潜表示为条件的条件得分函数。这两个步骤各自遵循其对应的对称性,并且可通过施加滤波反投影公式中存在的秩结构来实现压缩。实验表明,我们的框架兼具低样本复杂度和低计算复杂度,其参数量仅随目标分辨率呈次线性增长,且训练动态稳定。它能轻松生成清晰的重建结果,甚至可在多重散射场景下恢复亚奈奎斯特特征。

英文摘要:

We present Wideband Back-Projection Diffusion, an end-to-end probabilistic framework for approximating the posterior distribution induced by the inverse scattering map from wideband scattering data. This framework produces highly accurate reconstructions, leveraging conditional diffusion models to draw samples, and also honors the symmetries of the underlying physics of wave-propagation. The procedure is factored into two steps: the first step, inspired by the filtered back-propagation formula, transforms data into a physics-based latent representation, while the second step learns a conditional score function conditioned on this latent representation. These two steps individually obey their associated symmetries and are amenable to compression by imposing the rank structure found in the filtered back-projection formula. Empirically, our framework has both low sample and computational complexity, with its number of parameters scaling only sub-linearly with the target resolution, and has stable training dynamics. It provides sharp reconstructions effortlessly and is capable of recovering even sub-Nyquist features in the multiple-scattering regime.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑