NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Han, Yufei, Guo, Heng, Fukai, Koki, Santo, Hiroaki, Shi, Boxin, Okura, Fumio, Ma, Zhanyu, Jia, Yunpeng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911913582002176
author Han, Yufei
Guo, Heng
Fukai, Koki
Santo, Hiroaki
Shi, Boxin
Okura, Fumio
Ma, Zhanyu
Jia, Yunpeng
author_facet Han, Yufei
Guo, Heng
Fukai, Koki
Santo, Hiroaki
Shi, Boxin
Okura, Fumio
Ma, Zhanyu
Jia, Yunpeng
contents We present NeRSP, a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. Reflective surface reconstruction is extremely challenging as specular reflections are view-dependent and thus violate the multiview consistency for multiview stereo. On the other hand, sparse image inputs, as a practical capture setting, commonly cause incomplete or distorted results due to the lack of correspondence matching. This paper jointly handles the challenges from sparse inputs and reflective surfaces by leveraging polarized images. We derive photometric and geometric cues from the polarimetric image formation model and multiview azimuth consistency, which jointly optimize the surface geometry modeled via implicit neural representation. Based on the experiments on our synthetic and real datasets, we achieve the state-of-the-art surface reconstruction results with only 6 views as input.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07111
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images
Han, Yufei
Guo, Heng
Fukai, Koki
Santo, Hiroaki
Shi, Boxin
Okura, Fumio
Ma, Zhanyu
Jia, Yunpeng
Computer Vision and Pattern Recognition
We present NeRSP, a Neural 3D reconstruction technique for Reflective surfaces with Sparse Polarized images. Reflective surface reconstruction is extremely challenging as specular reflections are view-dependent and thus violate the multiview consistency for multiview stereo. On the other hand, sparse image inputs, as a practical capture setting, commonly cause incomplete or distorted results due to the lack of correspondence matching. This paper jointly handles the challenges from sparse inputs and reflective surfaces by leveraging polarized images. We derive photometric and geometric cues from the polarimetric image formation model and multiview azimuth consistency, which jointly optimize the surface geometry modeled via implicit neural representation. Based on the experiments on our synthetic and real datasets, we achieve the state-of-the-art surface reconstruction results with only 6 views as input.
title NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.07111