Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
This work addresses the challenge of 3D content creation from single images for applications in computer vision and graphics, representing an incremental advancement by integrating symmetry detection with existing generative models.
The paper tackled the problem of detecting 3D reflection symmetry from a single RGB image and applied it to improve single-image 3D generation, achieving a new state-of-the-art in symmetry detection and enhancing structural accuracy and visual fidelity in 3D reconstructions.
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.