Marius Cordts

Publications16
h-index7
Citations4,101
Highly Influential Citations990
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Uwe Franke
  • 109 Publications, 7,604 Citations
  • R. Urtasun
  • 272 Publications, 29,850 Citations
  • M. Enzweiler
  • 38 Publications, 6,717 Citations
  • Ross B. Girshick
  • 107 Publications, 114,890 Citations
  • 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
  • 3,702
  • 954
  • 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
  • 119
  • 16
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
  • 132
  • 11
  • PDF
Semantic Stixels: Depth is not enough
TLDR
We present Semantic Stixels, a novel vision-based scene model geared towards automated driving. Expand
  • 65
  • 5
  • PDF
Understanding Cityscapes: Efficient Urban Semantic Scene Understanding
TLDR
Semantic scene understanding plays a prominent role in the environment perception of autonomous vehicles. Expand
  • 6
  • 2
The Stixel World: A medium-level representation of traffic scenes
TLDR
We propose a medium-level model of the environment that is specifically designed to compress information about obstacles by leveraging the typical layout of outdoor traffic scenes. Expand
  • 34
  • 1
  • PDF
Object-Level Priors for Stixel Generation
TLDR
This paper presents a stereo vision-based scene model for traffic scenarios that combines bottom-up image segmentation with object-level knowledge in a sound probabilistic fashion. Expand
  • 18
  • 1
  • PDF
Tree-Structured Models for Efficient Multi-Cue Scene Labeling
TLDR
We propose a novel approach to semantic scene labeling in urban scenarios, which aims to combine excellent recognition performance with highest levels of computational efficiency. Expand
  • 11
Pixel-level encoding and depth layering for instance-level semantic segmentation
  • 7
Assessment of diastolic dysfunction in the transplanted heart with analysis of pixel-based deformation fields on CMR
Background Diastolic dysfunction is often used as a marker for allograft rejection and may even precede systolic abnormalities. However, diastolic indices provided by echocardiography can be of… Expand
  • 2