Abstract: Neural vocoders often struggle with aliasing in latent feature spaces, caused by time-domain nonlinear operations and resampling layers. Aliasing folds high-frequency components into the low ...

SHeaP learns to predict head geometry (FLAME parameters) from a single image, by predicting and rendering 2D Gaussians. This repository contains code and models for the FLAME parameter inference only.

Abstract: Multistatic millimeter-wave (MMW) imaging systems offer advantages in imaging objects with high contour complexity. Traditional reconstruction algorithms, such as the Back Projection (BP) ...

Unification: Otary offers a cohesive solution for image and geometry manipulation, letting you work seamlessly without switching tools. Readability: Self-explanatory by design. Otary’s clean, readable ...