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

## TL;DR

This paper introduces a novel neural network layer called Stacked Dilated Convolution (SDC) that captures large context regions with high spatial resolution, improving dense matching tasks like disparity and flow estimation.

## Contribution

The paper proposes a unified descriptor network using SDC layers that outperform existing descriptors in accuracy and robustness for dense matching tasks.

## Key findings

- SDC features outperform state-of-the-art descriptors in accuracy and robustness.
- SDC improves performance in stereo matching, optical flow, and scene flow benchmarks.
- The network maintains high spatial resolution with a large receptive field.

## 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.