by Martina Haefeli | Sep 8, 2018 | Video Processing, Visual Computing
On Regularized Losses for Weakly-supervised CNN Segmentation This paper proposes and experimentally compares different losses integrating MRF/CRF regularization terms. September 8, 2018European Conference on Computer Vision (ECCV) 2018 Authors Meng Tang...
by Martina Haefeli | Sep 4, 2018 | Video Processing, Visual Computing
Deep Video Color Propagation In this work we propose a deep learning framework for color propagation that combines a local strategy, to propagate colors frame-by-frame ensuring temporal stability, and a global strategy, using semantics for color propagation within a...
by Martina Haefeli | Aug 27, 2018 | Robotics, Story Technology, Visual Computing
Expressing Coherent Personality with Incremental Acquisition of Multimodal Behaviors We demonstrate the efficacy of the approach through a four-day study in which teams of participants interacted with a social robot expressing one of two personalities as the host of...
by Martina Haefeli | Aug 27, 2018 | Machine Learning, Rendering, Visual Computing
Denoising Deep Monte Carlo Renderings We present a novel algorithm to denoise deep Monte Carlo renderings, in which pixels contain multiple color values, each for a different range of depths. August 27, 2018EU Computer Graphics Forum (EU CGF) 2018 Authors...
by Martina Haefeli | Aug 9, 2018 | Capture, Visual Computing, Wireless Communication and Ubiquitous Computing
An Omnistereoscopic Video Pipeline for Capture and Display of Real-World VR In this paper we describe a complete pipeline for the capture and display of real-world Virtual Reality video content, based on the concept of omnistereoscopic panoramas. August 9, 2018ACM...
