# Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry

arXiv: https://arxiv.org/abs/2505.24162 · HTML: https://mlsanity.com/paper/2505.24162/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 7 of 7)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models](https://mlsanity.com/paper/1910.06511/) (2019)
- [Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features](https://mlsanity.com/paper/2311.18113/) (2023)
- [3D Part Segmentation via Geometric Aggregation of 2D Visual Features](https://mlsanity.com/paper/2412.04247/) (2024)
- [Robust Symmetry Detection via Riemannian Langevin Dynamics](https://mlsanity.com/paper/2410.02786/) (2024)
- [A dataset-free approach for self-supervised learning of 3D reflectional symmetries](https://mlsanity.com/paper/2503.02660/) (2025)
- [Probably Approximately Symmetric: Fast rigid Symmetry Detection with Global Guarantees](https://mlsanity.com/paper/1403.6637/) (2014)

## Abstract (arXiv)

We present a simple yet effective training-free approach for zero-shot 3D symmetry detection that leverages visual features from foundation vision models such as DINOv2. Our method extracts features from rendered views of 3D objects and backprojects them onto the original geometry. We demonstrate the symmetric invariance of these features and use them to identify reflection-symmetry planes through a proposed algorithm. Experiments on a subset of ShapeNet demonstrate that our approach outperforms both traditional geometric methods and learning-based approaches without requiring any training data. Our work demonstrates how foundation vision models can help in solving complex 3D geometric problems such as symmetry detection.