by America Ortiz | Dec 9, 2023 | Video Processing, Visual Computing
Empowering Convolutional Neural Networks with MetaSin Activation In this work, we propose replacing a baseline network’s existing activations with a novel ensemble function with trainable parameters. The proposed METASIN activation can be trained reliably without...
by America Ortiz | Nov 29, 2023 | Capture, Visual Computing
An Implicit Physical Face Model Driven by Expression and Style We propose a new face model based on a data-driven implicit neural physics model that can be driven by both expression and style separately. At the core, we present a framework for learning implicit...
by America Ortiz | Oct 28, 2023 | Video Processing, Visual Computing
Neural Video Compression with Spatio-Temporal Cross-Covariance Transformers This work aims to effectively and jointly leverage robust temporal and spatial information by proposing a new 3D-based transformer module: Spatio-Temporal Cross- Covariance Transformer...
by America Ortiz | Oct 9, 2023 | Capture, Visual Computing
A Perceptual Shape Loss for Monocular 3D Face Reconstruction In this work, we propose a new loss function for monocular face capture, inspired by how humans would perceive the quality of a 3D face reconstruction given a particular image. It is widely known that...
by America Ortiz | Oct 2, 2023 | Machine Learning
Controllable Inversion of Black-Box Face Recognition Models via Diffusion We tackle the challenging task of inverting the latent space of pre-trained face recognition models without full model access (i.e. black-box setting). Our method, the identity denoising...