Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiang, Huang, Zixuan, Thai, Anh, Rehg, James M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917849615826944
author Li, Xiang
Huang, Zixuan
Thai, Anh
Rehg, James M.
author_facet Li, Xiang
Huang, Zixuan
Thai, Anh
Rehg, James M.
contents Symmetry is a ubiquitous and fundamental property in the visual world, serving as a critical cue for perception and structure interpretation. This paper investigates the detection of 3D reflection symmetry from a single RGB image, and reveals its significant benefit on single-image 3D generation. We introduce Reflect3D, a scalable, zero-shot symmetry detector capable of robust generalization to diverse and real-world scenarios. Inspired by the success of foundation models, our method scales up symmetry detection with a transformer-based architecture. We also leverage generative priors from multi-view diffusion models to address the inherent ambiguity in single-view symmetry detection. Extensive evaluations on various data sources demonstrate that Reflect3D establishes a new state-of-the-art in single-image symmetry detection. Furthermore, we show the practical benefit of incorporating detected symmetry into single-image 3D generation pipelines through a symmetry-aware optimization process. The integration of symmetry significantly enhances the structural accuracy, cohesiveness, and visual fidelity of the reconstructed 3D geometry and textures, advancing the capabilities of 3D content creation.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17763
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
Li, Xiang
Huang, Zixuan
Thai, Anh
Rehg, James M.
Computer Vision and Pattern Recognition
Symmetry is a ubiquitous and fundamental property in the visual world, serving as a critical cue for perception and structure interpretation. This paper investigates the detection of 3D reflection symmetry from a single RGB image, and reveals its significant benefit on single-image 3D generation. We introduce Reflect3D, a scalable, zero-shot symmetry detector capable of robust generalization to diverse and real-world scenarios. Inspired by the success of foundation models, our method scales up symmetry detection with a transformer-based architecture. We also leverage generative priors from multi-view diffusion models to address the inherent ambiguity in single-view symmetry detection. Extensive evaluations on various data sources demonstrate that Reflect3D establishes a new state-of-the-art in single-image symmetry detection. Furthermore, we show the practical benefit of incorporating detected symmetry into single-image 3D generation pipelines through a symmetry-aware optimization process. The integration of symmetry significantly enhances the structural accuracy, cohesiveness, and visual fidelity of the reconstructed 3D geometry and textures, advancing the capabilities of 3D content creation.
title Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17763