by Martina Megaro | Jul 9, 2018 | Machine Learning
Quasi Monte Carlo Variational Inference We propose variance reduction by means of Quasi-Monte Carlo (QMC) sampling. July 9, 2018International Conference on Machine Learning (ICML) 2018 Authors Alexander Buchholz (ENSAE-CREST) Florian Wenzel (Humboldt...
by Martina Megaro | Jul 9, 2018 | Machine Learning, Visual Computing
Iterative Amortized Inference We demonstrate the inference optimization capabilities of iterative inference models and show that they outperform standard inference models on several benchmark data sets of images and text. July 9, 2018International Conference on...
by Martina Megaro | Jun 27, 2018 | Machine Learning, Robotics
Automated Deep Reinforcement Learning Environment for Hardware of a Modular Legged Robot We present an automated learning environment for developing control policies directly on the hardware of a modular legged robot. June 27, 2018International Conference on...
by Martina Megaro | Apr 30, 2018 | Video Processing, Visual Computing
Compressed Animated Light Fields with Real-time View-dependent Reconstruction We propose an end-to-end solution for presenting movie quality animated graphics to the user while still allowing the sense of presence afforded by free viewpoint head motion. April 30,...
by Martina Megaro | Apr 16, 2018 | Capture, Visual Computing
From Faces to Outdoor Light Probes This paper presents an approach to directly estimate an HDR light probe from a single LDR photograph, shot outdoors with a consumer camera, without specialized calibration targets or equipment. April 16, 2018Eurographics 2018...
