Non-line-of-Sight Imaging via Neural Transient Fields

01/02/2021
by   Siyuan Shen, et al.
20

We present a neural modeling framework for Non-Line-of-Sight (NLOS) imaging. Previous solutions have sought to explicitly recover the 3D geometry (e.g., as point clouds) or voxel density (e.g., within a pre-defined volume) of the hidden scene. In contrast, inspired by the recent Neural Radiance Field (NeRF) approach, we use a multi-layer perceptron (MLP) to represent the neural transient field or NeTF. However, NeTF measures the transient over spherical wavefronts rather than the radiance along lines. We therefore formulate a spherical volume NeTF reconstruction pipeline, applicable to both confocal and non-confocal setups. Compared with NeRF, NeTF samples a much sparser set of viewpoints (scanning spots) and the sampling is highly uneven. We thus introduce a Monte Carlo technique to improve the robustness in the reconstruction. Comprehensive experiments on synthetic and real datasets demonstrate NeTF provides higher quality reconstruction and preserves fine details largely missing in the state-of-the-art.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

page 9

research
01/26/2021

Real-time Non-line-of-sight Imaging with Two-step Deep Remapping

Conventional imaging only records the photons directly sent from the obj...
research
09/17/2022

Neural Implicit Surface Reconstruction using Imaging Sonar

We present a technique for dense 3D reconstruction of objects using an i...
research
04/21/2023

Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction

We introduce Omni-LOS, a neural computational imaging method for conduct...
research
12/08/2020

ODFNet: Using orientation distribution functions to characterize 3D point clouds

Learning new representations of 3D point clouds is an active research ar...
research
03/06/2017

Fast Back-Projection for Non-Line of Sight Reconstruction

Recent works have demonstrated non-line of sight (NLOS) reconstruction b...
research
05/03/2022

Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging

Computational approach to imaging around the corner, or non-line-of-sigh...
research
01/24/2020

Deep Non-Line-of-Sight Reconstruction

The recent years have seen a surge of interest in methods for imaging be...

Please sign up or login with your details

Forgot password? Click here to reset