by Martina Megaro | May 25, 2020 | Capture, Digital Humans, Machine Learning
Fast Nonlinear Least Squares Optimization of Large-Scale Semi-Sparse Problems We introduce a novel iterative solver for nonlinear least squares optimization of large-scale semi-sparse problems. May 25, 2020Eurographics 2020 Authors Marco Fratarcangeli...
by Martina Megaro | Nov 4, 2019 | Video Processing, Visual Computing
Deep Generative Video Compression We propose an end-to-end, deep probabilistic modeling approach to compress low-resolution videos. Our approach builds upon variational autoencoder (VAE) models for sequential data and combines them with recent work on neural image...
by Martina Megaro | Jun 10, 2019 | Machine Learning
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation We propose a novel,polynomial-time approximation of Shapley values in deep neural networks. June 10, 2019International Conference on Machine Learning (ICML) 2019 ...
by Martina Megaro | Jun 1, 2019 | Animation, Story Technology, Visual Computing
Generating Animations from Screenplays In this paper, we develop a text-to-animation system which is capable of handling complex sentences. June 1, 2019*SEM 2019 Authors Yeyao Zhang (Disney Research/ETH Joint M.Sc.) Eleftheria Tsipidi (Disney Research) Sasha...
by Martina Megaro | May 28, 2019 | Machine Learning, Video Processing, Visual Computing
Learning-based Sampling for Natural Image Matting We present a new sampling-based natural matting tech- nique that utilizes a pair of novel sampling networks for estimating background and foreground colors of pixels in unknown image regions. June 16, 2019IEEE...
