Transformations Based on Continuous Piecewise-Affine Velocity Fields

Research output: Contribution to journalJournal article – Annual report year: 2017Researchpeer-review

Documents

DOI

View graph of relations

We propose novel finite-dimensional spaces of well-behaved 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
JournalI E E E Transactions on Pattern Analysis and Machine Intelligence
Volume39
Issue number12
Pages (from-to)2496-2509
ISSN0162-8828
DOIs
Publication statusPublished - 2017
CitationsWeb of Science® Times Cited: No match on DOI

    Research areas

  • Continuous piecewise-affine velocity fields, Diffeomorphisms, Tessellations, Priors, Spatial transformations

Download statistics

No data available

ID: 139267796