• Publications
  • Influence
The Cityscapes Dataset for Semantic Urban Scene Understanding
TLDR
We introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Expand
  • 3,854
  • 1008
  • PDF
The Stixel World - A Compact Medium Level Representation of the 3D-World
TLDR
We propose to represent the 3D-situation by a set of rectangular sticks named “stixels” as shown in Fig. 1(b). Expand
  • 185
  • 24
  • PDF
The Cityscapes Dataset
TLDR
We present ongoing work on a new large-scale dataset for (1) assessing the performance of vision algorithms for different tasks of semantic urban scene understanding, including scene labeling, instance-level scene labeling and object detection. Expand
  • 122
  • 16
Stereoscopic Scene Flow Computation for 3D Motion Understanding
TLDR
We propose a variational framework for the estimation of stereoscopic scene flow, i.e., the motion of points in the three-dimensional world from stereo image sequences. Expand
  • 171
  • 14
  • PDF
Efficient Dense Scene Flow from Sparse or Dense Stereo Data
TLDR
This paper presents a technique for estimating the three-dimensional velocity vector field that describes the motion of each visible scene point (scene flow). Expand
  • 187
  • 12
  • PDF
Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling
TLDR
We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Expand
  • 134
  • 11
  • PDF
RegNet: Multimodal sensor registration using deep neural networks
TLDR
In this paper, we present RegNet, the first deep convolutional neural network (CNN) to infer a 6 degrees of freedom (DOF) extrinsic calibration between multimodal sensors, exemplified using a scanning LiDAR. Expand
  • 42
  • 10
  • PDF
Towards a Global Optimal Multi-Layer Stixel Representation of Dense 3D Data
TLDR
Dense 3D data as delivered by stereo vision systems, modern laser scanners or timeof-flight cameras such as PMD is a key element for 3D scene understanding. Expand
  • 94
  • 8
  • PDF
Lost and Found: detecting small road hazards for self-driving vehicles
TLDR
We present and evaluate an efficient stereo-based method for detecting small but critical road hazards, such as lost cargo, for self–driving vehicles. Expand
  • 36
  • 8
  • PDF
Autonomous Driving Goes Downtown
TLDR
We introduce their intelligent Stop&Go system and discuss appropriate algorithms and approaches for vision-module control. Expand
  • 309
  • 7