Despite tremendous advancements in bird's-eye view (BEV) perception, exi...
We show how to build a model that allows realistic, free-viewpoint rende...
We present Sim-on-Wheels, a safe, realistic, and vehicle-in-loop framewo...
We build rearticulable models for arbitrary everyday man-made objects
co...
Controller tuning is a vital step to ensure the controller delivers its
...
Efficient ObjectGoal navigation (ObjectNav) in novel environments requir...
Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent
appr...
Recovering the skeletal shape of an animal from a monocular video is a
l...
The performance of a robot controller depends on the choice of its
param...
We present LiDARGen, a novel, effective, and controllable generative mod...
Recovering the spatial layout of the cameras and the geometry of the sce...
We present Neural Mixtures of Planar Experts (NeurMiPs), a novel planar-...
We present an efficient, effective, and generic approach towards solving...
In this paper, we introduce a non-parametric memory representation for
s...
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...
Existing multi-camera SLAM systems assume synchronized shutters for all
...
Scalable sensor simulation is an important yet challenging open problem ...
We consider the problem of generating realistic traffic scenes automatic...
We are interested in understanding whether retrieval-based localization
...
Creating high definition maps that contain precise information of static...
In this paper, we propose a novel 3D object detector that can exploit bo...
One of the main difficulties of scaling current localization systems to ...
In this paper we propose a real-time, calibration-agnostic and effective...
We present a novel compression algorithm for reducing the storage of LiD...
We propose a very simple and efficient video compression framework that ...
In this paper, we propose the Deep Structured self-Driving Network (DSDN...
We tackle the problem of producing realistic simulations of LiDAR point
...
We present a novel deep compression algorithm to reduce the memory footp...
In the past few years, we have seen great progress in perception algorit...
We propose a new family of efficient and expressive deep generative mode...
Our goal is to significantly speed up the runtime of current state-of-th...
In this paper we tackle the problem of stereo image compression, and lev...
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 tackle the problem of scene flow estimation in the cont...
In this paper we introduce the TorontoCity benchmark, which covers the f...
Finding visual correspondence between local features is key to many comp...
In this paper we present a robust, efficient and affordable approach to
...