Computer Vision

TACO: Taming Diffusion for in-the-wild Video Amodal Completion

GWM: Towards Scalable Gaussian World Models for Robotic Manipulation

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

PrimHOI: Compositional Human-Object Interaction via Reusable Primitives