• DOI:10.1007/978-3-319-45886-1_2
Corpus ID: 5571650

Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling

@inproceedings{Uhrig2016PixelLevelEA,
  title={Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling},
  author={J. Uhrig and Marius Cordts and Uwe Franke and T. Brox},
  booktitle={GCPR},
  year={2016}
}

J. Uhrig, Marius Cordts, +1 author T. Brox

Published in GCPR 2016

Computer Science

Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. 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. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed