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

04/05/2019
by   René Schuster, et al.
8

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.

READ FULL TEXT

page 16

page 17

page 18

page 19

page 21

page 22

page 25

page 29

research
07/09/2021

DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction

Dense pixel matching problems such as optical flow and disparity estimat...
research
04/12/2019

An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching

Training a deep neural network is a non-trivial task. Not only the tunin...
research
06/22/2020

ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching

Dense pixel matching is required for many computer vision algorithms suc...
research
03/07/2017

Optical Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation

Modern large displacement optical flow algorithms usually use an initial...
research
03/20/2018

Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences

Interest point descriptors have fueled progress on almost every problem ...
research
04/25/2019

A Conditional Adversarial Network for Scene Flow Estimation

The problem of Scene flow estimation in depth videos has been attracting...
research
04/12/2016

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

We present a global optimization approach to optical flow estimation. Th...

Please sign up or login with your details

Forgot password? Click here to reset