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 | Nov 1, 2019 | Machine Learning, Visual Computing
Differentiable Surface Splatting for Point-based Geometry Processing We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds. November 1, 2019ACM SIGGRAPH Asia 2019 AuthorsYifan Wang (ETH Zurich)Serena Felice...
by Martina Megaro | Nov 1, 2019 | Video Processing, Visual Computing
Blind image super resolution with spatially variant degradations We show how to extend our approach to spatially variant degradations that typically arise in visual effects pipelines when compositing content from different sources and how to enable both local and...
by Martina Megaro | Oct 27, 2019 | Animation, AR/VR, Visual Computing
Parameterized Animated Activities We propose a metadata representation that describes which aspects of an animation can be varied. October 28, 2019ACM MIG 2019 Authors Alba M. Rios Rodriguez (DisneyResearch|Studios/ETH Joint M.Sc.) Steven Poulakos...
by Sarah Frigg | Oct 27, 2019 | Video Processing, Visual Computing
Neural Inter-Frame Compression for Video Coding In this work we present an inter-frame compression approach for neural video coding that can seamlessly build up on different existing neural image codecs. October 27, 2019International Conference on Computer Vision...
