ImOV3D: LearningOpen-VocabularyPointClouds 3DObjectDetectionfromOnly2DImages
–Neural Information Processing Systems
Open-vocabulary 3D object detection (OV-3Det) aims to generalize beyond the limited number ofbasecategories labeled during thetraining phase. Thebiggest bottleneck is the scarcity of annotated 3D data, whereas 2D image datasets are abundantandrichlyannotated.
Neural Information Processing Systems
Feb-18-2026, 20:35:53 GMT
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Natural Language > Large Language Model (0.47)
- Vision (1.00)
- Information Technology > Artificial Intelligence