Saved in:
Bibliographic Details
Main Authors: Ichimaru, Kazuto, Ikeda, Takaki, Thomas, Diego, Iwaguchi, Takafumi, Kawasaki, Hiroshi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15376
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929551613886464
author Ichimaru, Kazuto
Ikeda, Takaki
Thomas, Diego
Iwaguchi, Takafumi
Kawasaki, Hiroshi
author_facet Ichimaru, Kazuto
Ikeda, Takaki
Thomas, Diego
Iwaguchi, Takafumi
Kawasaki, Hiroshi
contents 3D-shape reconstruction in extreme environments, such as low illumination or scattering condition, has been an open problem and intensively researched. Active stereo is one of potential solution for such environments for its robustness and high accuracy. However, active stereo systems usually consist of specialized system configurations with complicated algorithms, which narrow their application. In this paper, we propose Neural Signed Distance Field for active stereo systems to enable implicit correspondence search and triangulation in generalized Structured Light. With our technique, textureless or equivalent surfaces by low light condition are successfully reconstructed even with a small number of captured images. Experiments were conducted to confirm that the proposed method could achieve state-of-the-art reconstruction quality under such severe condition. We also demonstrated that the proposed method worked in an underwater scenario.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15376
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ActiveNeuS: Neural Signed Distance Fields for Active Stereo
Ichimaru, Kazuto
Ikeda, Takaki
Thomas, Diego
Iwaguchi, Takafumi
Kawasaki, Hiroshi
Computer Vision and Pattern Recognition
3D-shape reconstruction in extreme environments, such as low illumination or scattering condition, has been an open problem and intensively researched. Active stereo is one of potential solution for such environments for its robustness and high accuracy. However, active stereo systems usually consist of specialized system configurations with complicated algorithms, which narrow their application. In this paper, we propose Neural Signed Distance Field for active stereo systems to enable implicit correspondence search and triangulation in generalized Structured Light. With our technique, textureless or equivalent surfaces by low light condition are successfully reconstructed even with a small number of captured images. Experiments were conducted to confirm that the proposed method could achieve state-of-the-art reconstruction quality under such severe condition. We also demonstrated that the proposed method worked in an underwater scenario.
title ActiveNeuS: Neural Signed Distance Fields for Active Stereo
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.15376