• Publications
  • Influence
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. Expand
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. Expand
CARLA: An Open Urban Driving Simulator
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. Expand
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. Expand
Direct Sparse Odometry
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. Expand
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. Expand
Dilated Residual Networks
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. Expand
Learning to See in the Dark
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. Expand
Geodesic Object Proposals
An approach for identifying a set of candidate objects in a given image that can be used for object recognition, segmentation, and other object-based image parsing tasks is presented. Expand
Photographic Image Synthesis with Cascaded Refinement Networks
  • Qifeng Chen, V. Koltun
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 28 July 2017
It is shown that photographic images can be synthesized from semantic layouts by a single feedforward network with appropriate structure, trained end-to-end with a direct regression objective. Expand