BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing Paper • 2506.17450 • Published 10 days ago • 42
Multi3DRefer: Grounding Text Description to Multiple 3D Objects Paper • 2309.05251 • Published Sep 11, 2023
Duoduo CLIP: Efficient 3D Understanding with Multi-View Images Paper • 2406.11579 • Published Jun 17, 2024
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning Paper • 2506.13654 • Published 14 days ago • 42