Rigorously testing autonomy systems is essential for making safe self-dr...
Inferring past human motion from RGB images is challenging due to the
in...
In recent years, transformer-based detectors have demonstrated remarkabl...
Humans form mental images of 3D scenes to support counterfactual imagina...
Recovering the spatial layout of the cameras and the geometry of the sce...
We present Neural Mixtures of Planar Experts (NeurMiPs), a novel planar-...
Neural Radiance Fields (NeRF) have recently gained a surge of interest w...
We present an efficient, effective, and generic approach towards solving...
Reconstructing high-fidelity 3D objects from sparse, partial observation...
Standard convolutional neural networks assume a grid structured input is...
Constructing and animating humans is an important component for building...
Annotating videos with object segmentation masks typically involves a tw...
One of the fundamental challenges to scale self-driving is being able to...
In this paper, we tackle the problem of online road network extraction f...
Creating high definition maps that contain precise information of static...
Sensor simulation is a key component for testing the performance of
self...
We propose a very simple and efficient video compression framework that ...
3D shape completion for real data is important but challenging, since pa...
Obtaining precise instance segmentation masks is of high importance in m...
We tackle the problem of producing realistic simulations of LiDAR point
...
In this paper, we propose PolyTransform, a novel instance segmentation
a...
Our goal is to significantly speed up the runtime of current state-of-th...
In this paper we propose a novel semantic localization algorithm that
ex...
In this paper we tackle the problem of scene flow estimation in the cont...
Sounds originate from object motions and vibrations of surrounding air.
...
We tackle the problem of using 3D information in convolutional neural
ne...
In this paper we present a robust, efficient and affordable approach to
...
We develop predictive models of pedestrian dynamics by encoding the coup...