2 papers
cs.CV2024
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting
Hao Liu, Minglin Chen, Yanni Ma +2
Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing…
cs.CV2024
3D Scene Graph Guided Vision-Language Pre-training
Hao Liu, Yanni Ma, Yan Liu +2
3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typi…