Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
Published in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Recommended citation: An, Z., Sun, G., Liu, Y., Li, R., Han, J., Konukoglu, E., & Belongie, S. (2025). Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model. In CVPR. https://openaccess.thecvf.com/content/CVPR2025/papers/An_Generalized_Few-shot_3D_Point_Cloud_Segmentation_with_Vision-Language_Model_CVPR_2025_paper.pdf
A generalized few-shot 3D segmentation framework that combines sparse annotations with knowledge from 3D vision-language models.