Johannes Ballé
Eero Simoncelli’s lab at NYU

Density Modeling of Images using a Generalized Divisive Normalization Transformation

Friday 19th of February 2016 at 11:00am
560 Evans

We introduce a parametric nonlinear transformation for jointly Gaussianizing patches of natural images. The transformation is differentiable, can be efficiently inverted, and thus induces a density model. It generalizes and performs better than several previous image models such as ICA, radial Gaussianization, and ISA. Model samples are visually similar to natural image patches. We use the model for image restoration, and show that it can be cascaded to build nonlinear hierarchies analogous to multiscale representations.
(video)

Join Email List

You can subscribe to our weekly seminar email list by sending an email to majordomo@lists.berkeley.edu that contains the words subscribe redwood in the body of the message.
(Note: The subject line can be arbitrary and will be ignored)