Share This Author
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
This paper considers fully connected CRF models defined on the complete set of pixels in an image and proposes a highly efficient approximate inference algorithm in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels.
CARLA: An Open Urban Driving Simulator
- A. Dosovitskiy, G. Ros, Felipe Codevilla, Antonio M. López, V. Koltun
- Computer ScienceCoRL
- 18 October 2017
This work introduces CARLA, an open-source simulator for autonomous driving research, and uses it to study the performance of three approaches to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end to-end models trained via reinforcement learning.
Multi-Scale Context Aggregation by Dilated Convolutions
This work develops a new convolutional network module that is specifically designed for dense prediction, and shows that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems.
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
A systematic evaluation of generic convolutional and recurrent architectures for sequence modeling concludes that the common association between sequence modeling and recurrent networks should be reconsidered, and convolutionals should be regarded as a natural starting point for sequence modeled tasks.
Direct Sparse Odometry
- Jakob J. Engel, V. Koltun, D. Cremers
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 9 July 2016
The experiments show that the presented approach significantly outperforms state-of-the-art direct and indirect methods in a variety of real-world settings, both in terms of tracking accuracy and robustness.
Playing for Data: Ground Truth from Computer Games
It is shown that associations between image patches can be reconstructed from the communication between the game and the graphics hardware, which enables rapid propagation of semantic labels within and across images synthesized by the game, with no access to the source code or the content.
Dilated Residual Networks
- F. Yu, V. Koltun, T. Funkhouser
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 28 May 2017
It is shown that dilated residual networks (DRNs) outperform their non-dilated counterparts in image classification without increasing the models depth or complexity and the accuracy advantage of DRNs is further magnified in downstream applications such as object localization and semantic segmentation.
Habitat: A Platform for Embodied AI Research
- M. Savva, Abhishek Kadian, Dhruv Batra
- Computer ScienceIEEE/CVF International Conference on Computer…
- 2 April 2019
The comparison between learning and SLAM approaches from two recent works are revisited and evidence is found -- that learning outperforms SLAM if scaled to an order of magnitude more experience than previous investigations, and the first cross-dataset generalization experiments are conducted.
On Evaluation of Embodied Navigation Agents
The present document summarizes the consensus recommendations of a working group to study empirical methodology in navigation research and discusses different problem statements and the role of generalization, present evaluation measures, and provides standard scenarios that can be used for benchmarking.
Learning to See in the Dark
- Chen Chen, Qifeng Chen, Jia Xu, V. Koltun
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 4 May 2018
A pipeline for processing low-light images is developed, based on end-to-end training of a fully-convolutional network that operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data.