GVC-Seg

GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence

Announce Type: new Abstract: Accurate 3D instance segmentation in point cloud data is critical for machine vision applications. Recent advancements leverage multiple pre-trained foundation models to generate 3D proposals, followed by the application of proposal aggregation methods, which significantly enhance performance. However, they often produce sub-optimal results due to inherent variations in confidence levels across different segmentation models, resulting in a bias toward the model...