Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It Simple

Oren Freifeld, Søren Hauberg, Kayhan Batmanghelich, John W. Fisher

Research output: Contribution to conferencePaperResearchpeer-review

649 Downloads (Pure)


We propose novel finite-dimensional spaces of Rn → Rn transformations, n ∈ {1, 2, 3}, derived from (continuously-defined) parametric stationary velocity fields. Particularly, we obtain these transformations, which are diffeomorphisms, by fast and highly-accurate integration of continuous piecewise-affine velocity fields; we also provide an ex-act solution for n = 1. The simple-yet-highly-expressive proposed representation handles optional constraints (e.g., volume preservation) easily and supports convenient modeling choices and rapid likelihood evaluations (facilitating tractable inference over latent transformations). Its applications include, but are not limited to: unconstrained optimization over monotonic functions; modeling cumulative distribution functions or histograms; time warping; image registration; landmark-based warping; real-time diffeomorphic image editing.
Original languageEnglish
Publication date2015
Number of pages9
Publication statusPublished - 2015
Event15th International Conference on Computer Vision - Santiago, Chile
Duration: 11 Dec 201518 Dec 2015
Conference number: 15


Conference15th International Conference on Computer Vision
Internet address

Bibliographical note

© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including
reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.


Dive into the research topics of 'Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It Simple'. Together they form a unique fingerprint.

Cite this