Non-line-of-sight imaging via Physics-informed Cascade Learning

Engineering notes

Validated on both synthetic and experimental datasets, PICL demonstrates superior robustness under low-SNR conditions, achieving performance improvement over the state-of-the-art methods.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Non-line-of-sight (NLOS) imaging enables the reconstruction of hidden scenes by analyzing indirectly reflected light, with broad applications in autonomous driving, security monitoring, and rescue operations. However, high-fidelity reconstruction is often hindered by the coupling of single-photon avalanche diode (SPAD) detector noises (e.g., dark count rate, and time jitter) and the intrinsic ill-posedness of the underlying inversion problem. We propose a Physics-informed Cascade Learning (PICL) method, a framework that integrates model-driven denoising with self-supervised, physics-informed reconstructions. PICL employs a lightweight, SPAD-specific noise separation network to decouple signal from mixed interference, followed by a reconstruction network that embeds a differentiable forward physical model. This architecture eliminates the need for NLOS large-scale paired datasets while preserving physical consistency. Validated on both synthetic and experimental datasets, PICL demonstrates superior robustness under low-SNR conditions, achieving performance improvement over the state-of-the-art methods. By bridging hardware constraints with algorithmic adaptability, this work provides a scalable and robust paradigm for high-resolution NLOS imaging.

Links and sources

Comments