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

By René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker. 2019

53 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Victor S. Lempitsky
2. Christian Häne
3. Marc Pollefeys

In Computer Vision and Pattern Recognition

1. Arsenii Ashukha
2. Elizaveta Logacheva
3. Roman Suvorov
4. Anton Mashikhin
5. Aleksei Silvestrov
6. Victor S. Lempitsky
7. Harshith Goka
8. Kiwoong Park

Citations in the corpus

• Resolution-robust Large Mask Inpainting with Fourier Convolutions (2021, methodology): “One variant of our approach relies heavily on dilated convolutional blocks, inspired by [41].”