-
[pdf]
[supp]
[bibtex]@InProceedings{Yen_2026_WACV, author = {Yen, Hong-Xuan and Chen, Chiamin and Wang, Yanqing and Liu, Yu-Lun and Sun, Min}, title = {PS3: Part Level Instance Segmentation in 3D}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {March}, year = {2026}, pages = {898-906} }
PS3: Part Level Instance Segmentation in 3D
Abstract
Open-vocabulary 3D segmentation allows exploration of 3D environments using unrestricted natural language queries. Current approaches to open-vocabulary 3D instance segmentation largely concentrate on recognizing object-level instances but face difficulties when dealing with more fine-grained elements of a scene, such as object parts. Some previous work constructs hierarchical open-vocabulary 3D scene representations by geometric over-segmentation, which can't identify parts with similar geometry. In this work, we introduce PS3, an approach to generate 3D part proposals from multi-view 2D masks. PS3 outperforms baselines that rely on geometric over-segmentation in scene-scale open-vocabulary 3D part segmentation.
Related Material
