ARM: Appearance Reconstruction Model for Relightable 3D Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Feng, Xiang, Yu, Chang, Bi, Zoubin, Shang, Yintong, Gao, Feng, Wu, Hongzhi, Zhou, Kun, Jiang, Chenfanfu, Yang, Yin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909392886038528
author Feng, Xiang
Yu, Chang
Bi, Zoubin
Shang, Yintong
Gao, Feng
Wu, Hongzhi
Zhou, Kun
Jiang, Chenfanfu
Yang, Yin
author_facet Feng, Xiang
Yu, Chang
Bi, Zoubin
Shang, Yintong
Gao, Feng
Wu, Hongzhi
Zhou, Kun
Jiang, Chenfanfu
Yang, Yin
contents Recent image-to-3D reconstruction models have greatly advanced geometry generation, but they still struggle to faithfully generate realistic appearance. To address this, we introduce ARM, a novel method that reconstructs high-quality 3D meshes and realistic appearance from sparse-view images. The core of ARM lies in decoupling geometry from appearance, processing appearance within the UV texture space. Unlike previous methods, ARM improves texture quality by explicitly back-projecting measurements onto the texture map and processing them in a UV space module with a global receptive field. To resolve ambiguities between material and illumination in input images, ARM introduces a material prior that encodes semantic appearance information, enhancing the robustness of appearance decomposition. Trained on just 8 H100 GPUs, ARM outperforms existing methods both quantitatively and qualitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10825
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ARM: Appearance Reconstruction Model for Relightable 3D Generation
Feng, Xiang
Yu, Chang
Bi, Zoubin
Shang, Yintong
Gao, Feng
Wu, Hongzhi
Zhou, Kun
Jiang, Chenfanfu
Yang, Yin
Computer Vision and Pattern Recognition
Graphics
Recent image-to-3D reconstruction models have greatly advanced geometry generation, but they still struggle to faithfully generate realistic appearance. To address this, we introduce ARM, a novel method that reconstructs high-quality 3D meshes and realistic appearance from sparse-view images. The core of ARM lies in decoupling geometry from appearance, processing appearance within the UV texture space. Unlike previous methods, ARM improves texture quality by explicitly back-projecting measurements onto the texture map and processing them in a UV space module with a global receptive field. To resolve ambiguities between material and illumination in input images, ARM introduces a material prior that encodes semantic appearance information, enhancing the robustness of appearance decomposition. Trained on just 8 H100 GPUs, ARM outperforms existing methods both quantitatively and qualitatively.
title ARM: Appearance Reconstruction Model for Relightable 3D Generation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.10825