18.2k citations
- Istituto Ricerche Solari LocarnoCH38 papers
- ETH ZurichCH28 papers
- Institut für SonnenphysikDE21 papers
- Instituto de Astrofísica de CanariasES12 papers
- Universidad de La LagunaES12 papers
- Dalle Molle Institute for Artificial Intelligence ResearchCH10 papers
- Politecnico di MilanoIT10 papers
- University of AmsterdamNL10 papers
- University of ZurichCH10 papers
- Consejo Superior de Investigaciones CientíficasES9 papers
- Italian Institute of TechnologyIT8 papers
- Centre National de la Recherche ScientifiqueFR7 papers
8 papers · 1 filter
Towards Understanding Depth Perception in Foveated Rendering
Sophie Kergaßner, Taimoor Tariq, Piotr Didyk
The true vision for real-time virtual and augmented reality is reproducing our visual reality in its entirety on immersive displays. To this end, foveated rendering leverages the l…
Human Vision Constrained Super-Resolution
Volodymyr Karpenko, Taimoor Tariq, Jorge Condor +1
Modern deep-learning super-resolution (SR) techniques process images and videos independently of the underlying content and viewing conditions. However, the sensitivity of the huma…
Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems
Julian Moosmann, Hanna Mueller, Nicky Zimmerman +3
This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power…
Non-Rigid Puzzles
Or Litany, Emanuele Rodolà, Alex Bronstein +2
Shape correspondence is a fundamental problem in computer graphics and vision, with applications in various problems including animation, texture mapping, robotic vision, medical i…
Geometric deep learning on graphs and manifolds using mixture model CNNs
Federico Monti, Davide Boscaini, Jonathan Masci +3
Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particu…
Robust Principal Component Analysis on Graphs
Nauman Shahid, Vassilis Kalofolias, Xavier Bresson +2
Principal Component Analysis (PCA) is the most widely used tool for linear dimensionality reduction and clustering. Still it is highly sensitive to outliers and does not scale well…