Object-centric representations enable autonomous driving algorithms to r...
An accurate model of the environment and the dynamic agents acting in it...
The self driving challenge in 2021 is this century's technological equiv...
Semantic segmentation in autonomous driving predominantly focuses on lea...
Driving requires interacting with road agents and predicting their futur...
Semantic segmentation approaches are typically trained on large-scale da...
We present a novel deep learning architecture for probabilistic future
p...
We present a novel embedding approach for video instance segmentation. O...
Hand-crafting generalised decision-making rules for real-world urban
aut...
Simulation can be a powerful tool for understanding machine learning sys...
3D object detection from monocular images has proven to be an enormously...
We demonstrate the first application of deep reinforcement learning to
a...
Dropout is used as a practical tool to obtain uncertainty estimates in l...
Numerous deep learning applications benefit from multi-task learning wit...
Deep learning has shown to be effective for robust and real-time monocul...
There are two major types of uncertainty one can model. Aleatoric uncert...
We propose a novel deep learning architecture for regressing disparity f...
We present a deep learning framework for probabilistic pixel-wise semant...
We present a novel and practical deep fully convolutional neural network...
We present a robust and real-time monocular six degree of freedom
reloca...