Transformations Based on Continuous Piecewise-Affine Velocity Fields

Oren Freifeld, Soren Hauberg, Kayhan Batmanghelich, Jonn W. Fisher
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We propose novel finite-dimensional spaces of well-behaved R n ! R n 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
more » ... 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.
doi:10.1109/tpami.2016.2646685 pmid:28092517 pmcid:PMC5889303 fatcat:pi4znbaqebfubf3wdgdezt52by