3 code implementations • 20 May 2020 • Aseem Behl, Kashyap Chitta, Aditya Prakash, Eshed Ohn-Bar, Andreas Geiger
Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
no code implementations • CVPR 2019 • Aseem Behl, Despoina Paschalidou, Simon Donné, Andreas Geiger
In this paper, we propose to estimate 3D motion from such unstructured point clouds using a deep neural network.
no code implementations • ICCV 2017 • Aseem Behl, Omid Hosseini Jafari, Siva Karthik Mustikovela, Hassan Abu Alhaija, Carsten Rother, Andreas Geiger
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e. g., at texture-less or reflective surfaces.
no code implementations • 18 Apr 2017 • Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes.
no code implementations • CVPR 2014 • Aseem Behl, C. V. Jawahar, M. Pawan Kumar
The performance of binary classification tasks, such as action classification and object detection, is often measured in terms of the average precision (AP).