Robust Symmetry Detection via Riemannian Langevin Dynamics
This work addresses symmetry detection for computer vision and graphics applications, offering incremental improvements by integrating existing methods.
The paper tackled the problem of robust symmetry detection in shapes, which is challenging due to noise and partial symmetries, by proposing a method that combines classical techniques with generative modeling using Riemannian Langevin dynamics, resulting in improved robustness and ability to identify both partial and global symmetries.
Symmetries are ubiquitous across all kinds of objects, whether in nature or in man-made creations. While these symmetries may seem intuitive to the human eye, detecting them with a machine is nontrivial due to the vast search space. Classical geometry-based methods work by aggregating "votes" for each symmetry but struggle with noise. In contrast, learning-based methods may be more robust to noise, but often overlook partial symmetries due to the scarcity of annotated data. In this work, we address this challenge by proposing a novel symmetry detection method that marries classical symmetry detection techniques with recent advances in generative modeling. Specifically, we apply Langevin dynamics to a redefined symmetry space to enhance robustness against noise. We provide empirical results on a variety of shapes that suggest our method is not only robust to noise, but can also identify both partial and global symmetries. Moreover, we demonstrate the utility of our detected symmetries in various downstream tasks, such as compression and symmetrization of noisy shapes.