4 results found Sort:
[CVPR 2023] EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
Created
2022-09-30
4 commits to master branch, last one about a year ago
[CVPR2022 Oral] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
Created
2022-04-19
10 commits to main branch, last one 2 years ago
3DGraphLLM is a model that uses a 3D scene graph and an LLM to perform 3D vision-language tasks.
Created
2024-11-12
13 commits to main branch, last one about a month ago
SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
Created
2024-12-05
22 commits to master branch, last one about a month ago