Humans can easily imagine the complete 3D geometry of occluded objects a...
We propose a learning-based method to reconstruct the local terrain for
...
3D neural networks have become prevalent for many 3D vision tasks includ...
In this work, we propose a camera self-calibration algorithm for generic...
We introduce DiscoBox, a novel framework that jointly learns instance
se...
3D object detection has been widely studied due to its potential
applica...
Many problems in science and engineering can be formulated in terms of
g...
We present Deep Global Registration, a differentiable framework for pair...
We present a novel approach to reconstructing lightweight, CAD-based
rep...
In many robotics and VR/AR applications, 3D-videos are readily-available...
3D reconstruction from a single image is a key problem in multiple
appli...