Saved in:
Bibliographic Details
Main Authors: Wu, Tianhao, Liang, Hanxue, Zhong, Fangcheng, Riegler, Gernot, Vainer, Shimon, Deng, Jiankang, Oztireli, Cengiz
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.10083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915008959479808
author Wu, Tianhao
Liang, Hanxue
Zhong, Fangcheng
Riegler, Gernot
Vainer, Shimon
Deng, Jiankang
Oztireli, Cengiz
author_facet Wu, Tianhao
Liang, Hanxue
Zhong, Fangcheng
Riegler, Gernot
Vainer, Shimon
Deng, Jiankang
Oztireli, Cengiz
contents Implicit surface representations such as the signed distance function (SDF) have emerged as a promising approach for image-based surface reconstruction. However, existing optimization methods assume solid surfaces and are therefore unable to properly reconstruct semi-transparent surfaces and thin structures, which also exhibit low opacity due to the blending effect with the background. While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts. We present $α$Surf, a novel surface representation with decoupled geometry and opacity for the reconstruction of semi-transparent and thin surfaces where the colors mix. Ray-surface intersections on our representation can be found in closed-form via analytical solutions of cubic polynomials, avoiding Monte-Carlo sampling and is fully differentiable by construction. Our qualitative and quantitative evaluations show that our approach can accurately reconstruct surfaces with semi-transparent and thin parts with fewer artifacts, achieving better reconstruction quality than state-of-the-art SDF and NeRF methods. Website: https://alphasurf.netlify.app/
format Preprint
id arxiv_https___arxiv_org_abs_2303_10083
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle $α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity
Wu, Tianhao
Liang, Hanxue
Zhong, Fangcheng
Riegler, Gernot
Vainer, Shimon
Deng, Jiankang
Oztireli, Cengiz
Computer Vision and Pattern Recognition
Implicit surface representations such as the signed distance function (SDF) have emerged as a promising approach for image-based surface reconstruction. However, existing optimization methods assume solid surfaces and are therefore unable to properly reconstruct semi-transparent surfaces and thin structures, which also exhibit low opacity due to the blending effect with the background. While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts. We present $α$Surf, a novel surface representation with decoupled geometry and opacity for the reconstruction of semi-transparent and thin surfaces where the colors mix. Ray-surface intersections on our representation can be found in closed-form via analytical solutions of cubic polynomials, avoiding Monte-Carlo sampling and is fully differentiable by construction. Our qualitative and quantitative evaluations show that our approach can accurately reconstruct surfaces with semi-transparent and thin parts with fewer artifacts, achieving better reconstruction quality than state-of-the-art SDF and NeRF methods. Website: https://alphasurf.netlify.app/
title $α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.10083