Saved in:
Bibliographic Details
Main Authors: Li, Zhibing, Wu, Tong, Tan, Jing, Zhang, Mengchen, Wang, Jiaqi, Lin, Dahua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.12083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908293493948416
author Li, Zhibing
Wu, Tong
Tan, Jing
Zhang, Mengchen
Wang, Jiaqi
Lin, Dahua
author_facet Li, Zhibing
Wu, Tong
Tan, Jing
Zhang, Mengchen
Wang, Jiaqi
Lin, Dahua
contents Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics. Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs, while still struggling with inherent ambiguities between lighting and material. On the other hand, learning-based approaches leverage rich material priors from existing 3D object datasets but face challenges with maintaining multi-view consistency. In this paper, we introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations. Our method achieves accurate and multi-view consistent estimation on surface normals and material properties. This is made possible through a novel cross-view, cross-domain attention module and an illumination-augmented, view-adaptive training strategy. Additionally, we introduce ARB-Objaverse, a new dataset that provides large-scale multi-view intrinsic data and renderings under diverse lighting conditions, supporting robust training. Extensive experiments demonstrate that IDArb outperforms state-of-the-art methods both qualitatively and quantitatively. Moreover, our approach facilitates a range of downstream tasks, including single-image relighting, photometric stereo, and 3D reconstruction, highlighting its broad applications in realistic 3D content creation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12083
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
Li, Zhibing
Wu, Tong
Tan, Jing
Zhang, Mengchen
Wang, Jiaqi
Lin, Dahua
Computer Vision and Pattern Recognition
Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics. Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs, while still struggling with inherent ambiguities between lighting and material. On the other hand, learning-based approaches leverage rich material priors from existing 3D object datasets but face challenges with maintaining multi-view consistency. In this paper, we introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations. Our method achieves accurate and multi-view consistent estimation on surface normals and material properties. This is made possible through a novel cross-view, cross-domain attention module and an illumination-augmented, view-adaptive training strategy. Additionally, we introduce ARB-Objaverse, a new dataset that provides large-scale multi-view intrinsic data and renderings under diverse lighting conditions, supporting robust training. Extensive experiments demonstrate that IDArb outperforms state-of-the-art methods both qualitatively and quantitatively. Moreover, our approach facilitates a range of downstream tasks, including single-image relighting, photometric stereo, and 3D reconstruction, highlighting its broad applications in realistic 3D content creation.
title IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12083