Preprint
Aug 2026
3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning
Vision-Language Models align point clouds with image and text embeddings, enabling zero-shot recognition, retrieval, and open-vocabulary understanding of 3D shapes. Existing multimodal 3D pre-training methods produce fixed-dimensional embeddings, requiring separate models for different computational budgets. We propose...
M. Lobo, Vitor Matias, Jeová Farias et al.
· 1 citation