SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks
This work addresses the problem of dense matching for computer vision applications, offering a novel network design that improves performance in stereo matching, optical flow, and scene flow, though it is incremental in advancing descriptor networks.
The paper tackles dense pixel matching for computer vision tasks like disparity and flow estimation by introducing a unified descriptor network with stacked dilated convolutions (SDC), achieving superior accuracy and robustness compared to state-of-the-art methods on public benchmarks.
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.