3d environments
Three-dimensional simulated spaces used for training and evaluating AI systems, particularly in robotics and computer vision, to study spatial interactions and perception.
- BEDLAM2.0: Synthetic humans and cameras in motion
- BEDLAM2.0: Synthetic humans and cameras in motion
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
- Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
- Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs