2 papers
cs.CV2026
MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation
Yibo Zhao, Yigong Zhang, Jin Xie
Conventional 3D instance segmentation methods rely on labor-intensive 3D annotations for supervised training, which limits their scalability and generalization to novel objects. Re…
cs.CV2025
Sketchy Bounding-box Supervision for 3D Instance Segmentation
Qian Deng, Le Hui, Jin Xie +1
Bounding box supervision has gained considerable attention in weakly supervised 3D instance segmentation. While this approach alleviates the need for extensive point-level annotati…