SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks

Rene Schuster, Oliver Wasenmuller, Christian Unger, Didier Stricker; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2556-2565

Abstract


Dense pixel matching is important for many computer vision tasks such as disparity and flow estimation. We present a robust, unified descriptor network that considers a large context region with high spatial variance. Our network has a very large receptive field and avoids striding layers to maintain spatial resolution. These properties are achieved by creating a novel neural network layer that consists of multiple, parallel, stacked dilated convolutions (SDC). Several of these layers are combined to form our SDC descriptor network. In our experiments, we show that our SDC features outperform state-of-the-art feature descriptors in terms of accuracy and robustness. In addition, we demonstrate the superior performance of SDC in state-of-the-art stereo matching, optical flow and scene flow algorithms on several famous public benchmarks.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Schuster_2019_CVPR,
author = {Schuster, Rene and Wasenmuller, Oliver and Unger, Christian and Stricker, Didier},
title = {SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}