Fast Piecewise-Affine Motion Estimation Without Segmentation

02/06/2018
by   Denis Fortun, et al.
0

Current algorithmic approaches for piecewise affine motion estimation are based on alternating motion segmentation and estimation. We propose a new method to estimate piecewise affine motion fields directly without intermediate segmentation. To this end, we reformulate the problem by imposing piecewise constancy of the parameter field, and derive a specific proximal splitting optimization scheme. A key component of our framework is an efficient one-dimensional piecewise-affine estimator for vector-valued signals. The first advantage of our approach over segmentation-based methods is its absence of initialization. The second advantage is its lower computational cost which is independent of the complexity of the motion field. In addition to these features, we demonstrate competitive accuracy with other piecewise-parametric methods on standard evaluation benchmarks. Our new regularization scheme also outperforms the more standard use of total variation and total generalized variation.

READ FULL TEXT

page 6

page 7

page 8

page 9

page 10

research
03/21/2023

Sampling from a Gaussian distribution conditioned on the level set of a piecewise affine, continuous function

We consider how to use Hamiltonian Monte Carlo to sample from a distribu...
research
02/21/2017

An Efficient Four-Parameter Affine Motion Model for Video Coding

In this paper, we study a simplified affine motion model based coding fr...
research
07/13/2019

Motion Segmentation Using Locally Affine Atom Voting

We present a novel method for motion segmentation called LAAV (Locally A...
research
02/23/2023

Beyond Moments: Robustly Learning Affine Transformations with Asymptotically Optimal Error

We present a polynomial-time algorithm for robustly learning an unknown ...
research
01/06/2022

EM-driven unsupervised learning for efficient motion segmentation

This paper presents a CNN-based fully unsupervised method for motion seg...
research
08/16/2022

Delaunay-Triangulation-Based Learning with Hessian Total-Variation Regularization

Regression is one of the core problems tackled in supervised learning. R...
research
02/03/2023

Consistent and convergent discretizations of Helfrich-type energies on general meshes

We show that integral curvature energies on surfaces of the type E_0(M) ...

Please sign up or login with your details

Forgot password? Click here to reset