Recent research in multi-task learning reveals the benefit of solving re...
3D object detection has been widely studied due to its potential
applica...
An autonomous navigating agent needs to perceive and track the motion of...
We present JRDB, a novel dataset collected from our social mobile manipu...
A comprehensive semantic understanding of a scene is important for many
...
In many robotics and VR/AR applications, 3D-videos are readily-available...
Intersection over Union (IoU) is the most popular evaluation metric used...
3D semantic scene labeling is fundamental to agents operating in the rea...
3D reconstruction from a single image is a key problem in multiple
appli...
Supervised 3D reconstruction has witnessed a significant progress throug...
We present a deep learning framework for accurate visual correspondences...
Inspired by the recent success of methods that employ shape priors to ac...