Object rearrangement is pivotal in robotic-environment interactions,
rep...
Reconstructing hand-held objects from a single RGB image is an important...
In this paper, we present a novel shape reconstruction method leveraging...
Controllable scene synthesis aims to create interactive environments for...
Learning-based methods to solve dense 3D vision problems typically train...
Reliable multi-agent trajectory prediction is crucial for the safe plann...
Despite monocular 3D object detection having recently made a significant...
6-DoF robotic grasping is a long-lasting but unsolved problem. Recent me...
In this paper, we introduce DA^2, the first large-scale dual-arm
dexteri...
Depth estimation is a core task in 3D computer vision. Recent methods
in...
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of...
Due to the difficulty in generating the effective descriptors which are
...
In this paper, we propose PASS3D to achieve point-wise semantic segmenta...
While many visual ego-motion algorithm variants have been proposed in th...