Pixel-level Encoding and Depth Layering for Instance-level Semantic Labeling
Abstract
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 segmentation on the street scene datasets KITTI and Cityscapes. Our approach outperforms existing works by a large margin and can additionally predict absolute distances of individual instances from a monocular image as well as a pixel-level semantic labeling.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2016
- DOI:
- 10.48550/arXiv.1604.05096
- arXiv:
- arXiv:1604.05096
- Bibcode:
- 2016arXiv160405096U
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- Accepted at GCPR 2016. Includes supplementary material