Neural Reconstruction through Scattering Media with Forward and Backward Losses

• Published in: IEEE International Conference on Computational Photography pp. 1 - 12
• Main Authors: Wang, Yuehan, Shen, Siyuan, Xia, Suan, Li, Ruiqian, Peng, Xingyue, Yu, Yanhua, Li, Shiying, Yu, Jingyi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.07.2023
• Subjects: Computational photography; Diffuse optical tomography; Integrated optics; Light scattering; Media; Neural implicit representation; Non-line-of-sight imaging; Optical losses; Photography; Tomography; Training
• ISSN: 2472-7636
• DOI: 10.1109/ICCP56744.2023.10233796

Reconstructing an object behind a scattering medium needs to tackle different light scatterings inside the medium and in the free space. Major approaches, e.g., diffuse optical tomography and non-line-of-sight imaging, address either of the light scatterings. Confocal diffuse tomography (CDT) considers the media acting as a diffuse kernel on the free-space scattering and recovers the object by deconvolving the inside-medium scattering. Inspired by CDT, we present a Neural De-Scatterer to solve this challenging problem. We exploit neural implicit fields to represent the the free-space scattering and use a multilayer perceptron (MLP) to learn the density and albedo of the hidden object. Furthermore, we tailor a bi-directional training strategy to optimize the MLP with forward and backward losses and employ hash encoding for memory and computation efficiency. The Neural De-Scatterer enables us to reconstruct objects at arbitrary resolution. Comprehensive experiments with synthetic and real measurements demonstrate that our Neural De-Scatterer outperforms state-of-the-art methods. Our data and code are publicly available.