相似性一致似然扩散实现从墙壁反射的隐藏人物检测
Similarity-Consistent Likelihood Diffusion enables Hidden Person Detection from Wall Reflections
将异方差伪似然融入确定性DDIM采样，并通过退火贝叶斯精度更新与扩散先验融合，为逆问题提供可复现且测量一致的生成式重建方案，可迁移到其他欠定视觉重建任务。
原文依据 incorporates this likelihood into deterministic DDIM sampling and fuses it with the diffusion prior via annealed Bayesian precision updating
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论非视距（NLOS）成像旨在从直接视线之外的间接光传输中恢复隐藏场景信息。现有的NLOS方法可大致分为主动和被动两类。主动方法依赖可控照明和时间分辨传感器，但其对专用且昂贵硬件的依赖限制了实际部署。被动方法则使用稳态或非受控的间接反射与常规传感器，但常受弱信号、不稳定观测和测量约束不足的困扰。本文提出相似性似然扩散网络（SLD-Net），用于从多曝光墙壁观测中进行角落相机隐藏人物成像。SLD-Net包含两个阶段：DeLi-Inversion估计初始重建和逐像素精度图以构建异方差伪似然，SiCo-Diffusion将该似然融入确定性DDIM采样，并通过退火贝叶斯精度更新与扩散先验融合，产生可复现且测量一致的重建。在Reflect-Corridor和Reflect-Room数据集上的实验表明，相较于通用、物理启发和NLOS专用基线，SLD-Net取得了一致性提升。在Reflect-Corridor上，SLD-Net将峰值信噪比从13.84提升至15.58 dB，并将弗雷歇初始距离从264.91降至73.54；在Reflect-Room上，将峰值信噪比从11.58提升至12.49 dB，并将弗雷歇初始距离从177.05降至26.89。
英文原文摘要 1498 字符
Non-line-of-sight (NLOS) imaging seeks to recover hidden-scene information from indirect light transport beyond the direct line of sight. Existing NLOS methods can be broadly categorized into active and passive approaches. Active methods rely on controlled illumination and time-resolved sensors, but their dependence on specialized and expensive hardware limits practical deployment. Passive methods instead use steady-state or uncontrolled indirect reflections with conventional sensors, but often suffer from weak signals, unstable observations, and insufficient measurement constraints. In this paper, we present the Similarity-Likelihood Diffusion Network (SLD-Net) for corner-camera hidden-person imaging from multi-exposure wall observations. SLD-Net consists of two stages: DeLi-Inversion estimates an initial reconstruction and a pixel-wise precision map to construct a heteroscedastic pseudo-likelihood, and SiCo-Diffusion incorporates this likelihood into deterministic DDIM sampling and fuses it with the diffusion prior via annealed Bayesian precision updating, producing reproducible and measurement-consistent reconstructions. Experiments on the Reflect-Corridor and Reflect-Room datasets demonstrate consistent improvements over generic, physics-inspired, and NLOS-specific baselines. SLD-Net improves PSNR from 13.84 to 15.58 dB and reduces FID from 264.91 to 73.54 on Reflect-Corridor, and improves PSNR from 11.58 to 12.49 dB and reduces FID from 177.05 to 26.89 on Reflect-Room.