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

TL;DR

This paper presents Reflect3D, a transformer-based, zero-shot symmetry detector that improves single-image 3D generation by leveraging symmetry cues, generative priors, and symmetry-aware optimization, achieving state-of-the-art results.

Contribution

The paper introduces Reflect3D, a scalable, zero-shot symmetry detection method that enhances 3D generation from single images by integrating symmetry information with generative priors.

Findings

Reflect3D achieves new state-of-the-art in symmetry detection accuracy.

Incorporating symmetry improves 3D reconstruction quality.

Symmetry-aware optimization enhances structural and visual fidelity.

Abstract

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.