OpenSUN3D
* *Open-Vocabulary 3D Scene Understanding
* Change You Want to See (Now in 3D), The
* CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
* CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
* Dynamic Texts From UAV Perspective Natural Images
* Learning to Prompt CLIP for Monocular Depth Estimation: Exploring the Limits of Human Language
OpenSUN3D24
* *Open-Vocabulary 3D Scene Understanding
* AffordanceLLM: Grounding Affordance from Vision Language Models
* Zero-Shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation