Generative Modeling

Topology Adaptive Snakes Improve Mask Generation for Image Inpainting

T-snake deformable models, which can segment complex-shaped structures, improve generated masks passed to a GAN for image inpainting

Learning Deep Generative Models with Short Run Inference Dynamics

Short Run MCMC sampling is utilized in a deep generative model with multiple layers of latent variables

Masters Thesis in Generative Modeling in Vision

Thesis for UCLA Computer Science Masters program currently in progress

Formulation of Variational Lower Bound and Application of VAE to MNIST Dataset

Formulation of the evidence lower bound (ELBO) for the variational autoencoder and an application to synthesizing binary images