LS-Net: 学习解决单目立体非线性最小二乘问题

Sep, 2018

LS-Net: 学习解决单目立体非线性最小二乘问题

LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo

Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J. Davison

TL;DR本研究提出了一种神经网络算法LS-Net，用于优化基于平方和的目标函数。该算法不需要手动设置正则化参数，能够有效地优化具有挑战性的运动立体视觉问题。

Abstract

sum-of-squares objective functions are very popular in computer vision algorithms. However, these objective functions are not always easy to optimize. The underlying assumptions made by solvers are often not satisfied and many problems are inherently ill-posed. In this paper, we propos