Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Yue, Fan, Ningjing, Skorokhodov, Ivan, Voynov, Oleg, Ignatyev, Savva, Burnaev, Evgeny, Wonka, Peter, Wang, Yiqun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913778713493504
author Fan, Yue
Fan, Ningjing
Skorokhodov, Ivan
Voynov, Oleg
Ignatyev, Savva
Burnaev, Evgeny
Wonka, Peter
Wang, Yiqun
author_facet Fan, Yue
Fan, Ningjing
Skorokhodov, Ivan
Voynov, Oleg
Ignatyev, Savva
Burnaev, Evgeny
Wonka, Peter
Wang, Yiqun
contents We develop a method that recovers the surface, materials, and illumination of a scene from its posed multi-view images. In contrast to prior work, it does not require any additional data and can handle glossy objects or bright lighting. It is a progressive inverse rendering approach, which consists of three stages. In the first stage, we reconstruct the scene radiance and signed distance function (SDF) with a novel regularization strategy for specular reflections. We propose to explain a pixel color using both surface and volume rendering jointly, which allows for handling complex view-dependent lighting effects for surface reconstruction. In the second stage, we distill light visibility and indirect illumination from the learned SDF and radiance field using learnable mapping functions. Finally, we design a method for estimating the ratio of incoming direct light reflected in a specular manner and use it to reconstruct the materials and direct illumination. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art in recovering surfaces, materials, and lighting without relying on any additional data.
format Preprint
id arxiv_https___arxiv_org_abs_2305_17929
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects
Fan, Yue
Fan, Ningjing
Skorokhodov, Ivan
Voynov, Oleg
Ignatyev, Savva
Burnaev, Evgeny
Wonka, Peter
Wang, Yiqun
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
We develop a method that recovers the surface, materials, and illumination of a scene from its posed multi-view images. In contrast to prior work, it does not require any additional data and can handle glossy objects or bright lighting. It is a progressive inverse rendering approach, which consists of three stages. In the first stage, we reconstruct the scene radiance and signed distance function (SDF) with a novel regularization strategy for specular reflections. We propose to explain a pixel color using both surface and volume rendering jointly, which allows for handling complex view-dependent lighting effects for surface reconstruction. In the second stage, we distill light visibility and indirect illumination from the learned SDF and radiance field using learnable mapping functions. Finally, we design a method for estimating the ratio of incoming direct light reflected in a specular manner and use it to reconstruct the materials and direct illumination. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art in recovering surfaces, materials, and lighting without relying on any additional data.
title Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2305.17929