DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features
This addresses the challenge of point cloud matching for non-rigid shapes, which is important for applications in computer vision and graphics, but appears incremental as it builds on existing learning-based methods with specific enhancements.
The paper tackled the problem of estimating dense correspondences between non-rigidly deformable point clouds by proposing DV-Matcher, a learning-based framework that injects pre-trained visual features and uses a deformation-based module, achieving state-of-the-art results on near-isometric, heterogeneous, partial, and noisy data.
In this paper, we present DV-Matcher, a novel learning-based framework for estimating dense correspondences between non-rigidly deformable point clouds. Learning directly from unstructured point clouds without meshing or manual labelling, our framework delivers high-quality dense correspondences, which is of significant practical utility in point cloud processing. Our key contributions are two-fold: First, we propose a scheme to inject prior knowledge from pre-trained vision models into geometric feature learning, which effectively complements the local nature of geometric features with global and semantic information; Second, we propose a novel deformation-based module to promote the extrinsic alignment induced by the learned correspondences, which effectively enhances the feature learning. Experimental results show that our method achieves state-of-the-art results in matching non-rigid point clouds in both near-isometric and heterogeneous shape collection as well as more realistic partial and noisy data.