Salvato in:
Dettagli Bibliografici
Autori principali: Qiao, Rukun, Kawasaki, Hiroshi, Zha, Hongbin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.12006
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909207230414848
author Qiao, Rukun
Kawasaki, Hiroshi
Zha, Hongbin
author_facet Qiao, Rukun
Kawasaki, Hiroshi
Zha, Hongbin
contents We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised differentiable rendering. Unlike passive vision, where joint estimation of radiance and geometry fields is necessary, we capitalize on known radiance fields from projected patterns in structured light systems. This enables isolated optimization of the geometry field, ensuring convergence and network efficacy with fixed device positioning. To enhance geometric fidelity, we incorporate an additional color loss based on object surfaces during training. Real-world experiments demonstrate our method's superiority in geometric performance for few-shot scenarios, while achieving comparable results with increased pattern availability.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12006
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Depth Reconstruction with Neural Signed Distance Fields in Structured Light Systems
Qiao, Rukun
Kawasaki, Hiroshi
Zha, Hongbin
Computer Vision and Pattern Recognition
We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised differentiable rendering. Unlike passive vision, where joint estimation of radiance and geometry fields is necessary, we capitalize on known radiance fields from projected patterns in structured light systems. This enables isolated optimization of the geometry field, ensuring convergence and network efficacy with fixed device positioning. To enhance geometric fidelity, we incorporate an additional color loss based on object surfaces during training. Real-world experiments demonstrate our method's superiority in geometric performance for few-shot scenarios, while achieving comparable results with increased pattern availability.
title Depth Reconstruction with Neural Signed Distance Fields in Structured Light Systems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.12006