J. Uhrig

Publications11
h-index7
Citations920
Highly Influential Citations147
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Kaiming He
  • 83 Publications, 142,705 Citations
  • Ross B. Girshick
  • 107 Publications, 114,890 Citations
  • B. Andres
  • 80 Publications, 3,663 Citations
  • B. Schiele
  • 518 Publications, 50,168 Citations
  • Publications
  • Influence
Sparsity Invariant CNNs
TLDR
In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data. Expand
  • 267
  • 79
  • PDF
DeMoN: Depth and Motion Network for Learning Monocular Stereo
TLDR
We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. Expand
  • 386
  • 48
  • 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
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications
TLDR
We state a combinatorial optimization problem whose feasible solutions define both a decomposition and a node labeling of a given graph. Expand
  • 82
  • 4
  • PDF
Box2Pix: Single-Shot Instance Segmentation by Assigning Pixels to Object Boxes
TLDR
We present an approach that achieves competitive results on the Cityscapes [1] and KITTI [2] datasets, while being twice as fast as any other existing approach. Expand
  • 32
  • 4
  • PDF
The effect of lubricant additives on the coefficient of friction in the flat-die test
Abstract The effectiveness of various lubricants and their additives in reducing the coefficient of friction in the flat-die test was examined. The load, relative velocity, the additives, the base… Expand
  • 11
  • 1
Pixel-level encoding and depth layering for instance-level semantic segmentation
  • 7
Supplementary Material for Sparsity Invariant CNNs
We find that Sparse Convolutions converge much faster than standard convolutions for most input-output-combinations, especially for those on Synthia with irregularly sparse depth input, as considered… Expand
Method and apparatus for determining a roadside parking area
TLDR
A method for determining a roadside parking area comprises steps of determining an initial position and an end position of the parking area wherein the parking between the initial location and the end position extends; of determining positions of a curve of a road in the area of the initial and final positions of parking lot; and mapping the parking lot with respect to the course of the road such that the parking depicted extends immediately adjacent to the road. Expand
Proceedings 26th Symposium ESVN‐ECVN