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

arXiv: https://arxiv.org/abs/1904.03076 · HTML: https://mlsanity.com/paper/1904.03076/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2019.

## Built on by (most cited first, 13 of 13)

- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [Efficient Regional Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2103.12934/) (2021)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [Fourier Document Restoration for Robust Document Dewarping and Recognition](https://mlsanity.com/paper/2203.09910/) (2022)
- [StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2212.00937/) (2022)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting](https://mlsanity.com/paper/2112.13050/) (2021)
- [DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction](https://mlsanity.com/paper/2107.04715/) (2021)
- [DVMN: Dense Validity Mask Network for Depth Completion](https://mlsanity.com/paper/2107.06709/) (2021)
- [Self-Supervised Training with Autoencoders for Visual Anomaly Detection](https://mlsanity.com/paper/2206.11723/) (2022)
- [Segmentation Guided Deep HDR Deghosting](https://mlsanity.com/paper/2207.01229/) (2022)

## Abstract (arXiv)

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.