Bird's-Eye View (BEV) features are popular intermediate scene representa...
Recent methods in self-supervised learning have demonstrated that
maskin...
In this paper, we introduce a non-parametric memory representation for
s...
In the past few years we have seen great advances in 3D object detection...
In this paper we propose a novel semantic localization algorithm that
ex...
Reliable and accurate lane detection has been a long-standing problem in...
In this paper, we propose a unified panoptic segmentation network (UPSNe...
The world is covered with millions of buildings, and precisely knowing e...
In this paper we introduce the TorontoCity benchmark, which covers the f...
Most contemporary approaches to instance segmentation use complex pipeli...
We tackle the problem of estimating optical flow from a monocular camera...