Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
Published in International Conference on Learning Representations (ICLR), 2025
Recommended citation: An, Z., Sun, G., Liu, Y., Li, R., Wu, M., Cheng, M.-M., Konukoglu, E., & Belongie, S. (2025). Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation. In ICLR. https://proceedings.iclr.cc/paper_files/paper/2025/file/8b21a7ea42cbcd1c29a7a88c444cce45-Paper-Conference.pdf
A multimodal few-shot 3D segmentation framework combining text, 2D image cues, and point clouds.