by Martina Megaro | Sep 2, 2019 | Machine Learning
Spectrogram Feature Losses for Music Source Separation In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. September 2, 2019Eusipco 2019 ...
by Martina Megaro | Jul 12, 2019 | Animation, AR/VR, Visual Computing
Tangent Space Optimization of Controls for Character Animation We formulate the control of interpolations in animation with positional constraints over time as a space-time optimization problem in the tangent space of the curves driving the animation controls. July...
by Martina Megaro | Jul 12, 2019 | Capture, VFX, Visual Computing
Accurate Markerless Jaw Tracking for Facial Performance Capture We present the first method to accurately track the invisible jaw based solely on the visible skin surface, without the need for any markers or augmentation of the actor. July 12, 2019ACM Siggraph 2019...
by Martina Megaro | Jul 12, 2019 | Rendering, Visual Computing
Neural Importance Sampling We propose to use deep neural networks for generating samples in Monte Carlo integration. July 12, 2019ACM Siggraph 2019 Authors Thomas Müller (Disney Research/ETH Joint PhD) Brian McWilliams (Disney Research) Fabrice Rousselle...
by Martina Megaro | Jun 16, 2019 | Machine Learning, Video Processing, Visual Computing
Neural Sequential Phrase Grounding (SeqGROUND) We propose an end-to-end approach for phrase grounding in images. June 16, 2019IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 Authors Pelin Dogan (Disney Research/ETH Joint PhD) Leonid...
