Transformations Based on Continuous Piecewise-Affine Velocity Fields

Oren Freifeld, Soren Hauberg, Kayhan Batmanghelich, Jonn W. Fisher

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

We propose novel finite-dimensional spaces of well-behaved Rn →Rn transformations. The latter are obtained by (fast and highly-accurate) integration of continuous piecewise-affine velocity fields. The proposed method is simple yet highly expressive, effortlessly handles optional constraints (e.g., volume preservation and/or boundary conditions), and supports convenient modeling choices such as smoothing priors and coarse-to-fine analysis. Importantly, the proposed approach, partly due to its rapid likelihood evaluations and partly due to its other properties, facilitates tractable inference over rich transformation spaces, including using Markov-Chain Monte-Carlo methods. Its applications include, but are not limited to: monotonic regression (more generally, optimization over monotonic functions); modeling cumulative distribution functions or histograms; time-warping; image warping; image registration; real-time diffeomorphic image editing; data augmentation for image classifiers. Our GPU-based code is publicly available.

Original languageEnglish
Article number7814343
Pages (from-to)2496-2509
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume39
Issue number12
DOIs
StatePublished - 1 Dec 2017

Keywords

  • MCMC
  • Spatial transformations
  • continuous piecewise-affine velocity fields
  • diffeomorphisms
  • priors
  • tessellations

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Transformations Based on Continuous Piecewise-Affine Velocity Fields'. Together they form a unique fingerprint.

Cite this