Imperial College London


Faculty of EngineeringDepartment of Computing

Senior Lecturer



+44 (0)20 7594 7123s.leutenegger Website




360ACE ExtensionSouth Kensington Campus






BibTex format

author = {Clark, R and Bloesch, M and Czarnowski, J and Leutenegger, S and Davison, AJ},
doi = {10.1007/978-3-030-01237-3_18},
pages = {291--306},
publisher = {Springer Nature Switzerland AG 2018},
title = {Learning to solve nonlinear least squares for monocular stereo},
url = {},
year = {2018}

RIS format (EndNote, RefMan)

AB - 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 propose a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities. Unlike traditional approaches, the proposed solver requires no hand-crafted regularizers or priors as these are implicitly learned from the data. We apply our method to the problem of motion stereo ie. jointly estimating the motion and scene geometry from pairs of images of a monocular sequence. We show that our learned optimizer is able to efficiently and effectively solve this challenging optimization problem.
AU - Clark,R
AU - Bloesch,M
AU - Czarnowski,J
AU - Leutenegger,S
AU - Davison,AJ
DO - 10.1007/978-3-030-01237-3_18
EP - 306
PB - Springer Nature Switzerland AG 2018
PY - 2018///
SN - 0302-9743
SP - 291
TI - Learning to solve nonlinear least squares for monocular stereo
UR -
UR -
ER -