Predictive online optimisation with applications to optical flow

by   Tuomo Valkonen, et al.

Online optimisation revolves around new data being introduced into a problem while it is still being solved; think of deep learning as more training samples become available. We adapt the idea to dynamic inverse problems such as video processing with optical flow. We introduce a corresponding predictive online primal-dual proximal splitting method. The video frames now exactly correspond to the algorithm iterations. A user-prescribed predictor describes the evolution of the primal variable. To prove convergence we need a predictor for the dual variable based on (proximal) gradient flow. This affects the model that the method asymptotically minimises. We show that for inverse problems the effect is, essentially, to construct a new dynamic regulariser based on infimal convolution of the static regularisers with the temporal coupling. We develop regularisation theory for dynamic inverse problems, and show the convergence of the algorithmic solutions in terms of this theory. We finish by demonstrating excellent real-time performance of our method in computational image stabilisation.



There are no comments yet.


page 22

page 29

page 30

page 31

page 32

page 34

page 35

page 36


Primal-dual block-proximal splitting for a class of non-convex problems

We develop block structure adapted primal-dual algorithms for non-convex...

Modular-proximal gradient algorithms in variable exponent Lebesgue spaces

We consider structured optimisation problems defined in terms of the sum...

Convergence rates and structure of solutions of inverse problems with imperfect forward models

The goal of this paper is to further develop an approach to inverse prob...

A deep primal-dual proximal network for image restoration

Image restoration remains a challenging task in image processing. Numero...

Error Analysis of Douglas-Rachford Algorithm for Linear Inverse Problems: Asymptotics of Proximity Operator for Squared Loss

Proximal splitting-based convex optimization is a promising approach to ...

An Outer-approximation Guided Optimization Approach for Constrained Neural Network Inverse Problems

This paper discusses an outer-approximation guided optimization method f...

A Statistical Theory of Deep Learning via Proximal Splitting

In this paper we develop a statistical theory and an implementation of d...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.