4 papers
ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
Jisoo Kim, Sangwon Baik, Taeksoo Kim +4
We present ZeroDex, a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB im…
SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image
Inhee Lee, Sangwon Baik, Sungjoo Kim +3
Reconstructing interactive, simulation-ready 3D scenes from a single image is a critical bottleneck for robotic manipulation. While recent single-image lifters recover plausible pe…
Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models
Sangwon Baik, Hyeonwoo Kim, Hanbyul Joo
We present a method for learning 3D spatial relationships between object pairs, referred to as object-object spatial relationships (OOR), by leveraging synthetically generated 3D s…
DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models
Hyeonwoo Kim, Sangwon Baik, Hanbyul Joo
Modeling how humans interact with objects is crucial for AI to effectively assist or mimic human behaviors. Existing studies for learning such ability primarily focus on static hum…