125 citations
- Sony Corporation (United States)US9 papers
- Graz University of TechnologyAT4 papers
- Dexerials (Japan)JP3 papers
- Keio UniversityJP3 papers
- Sony (Japan)JP3 papers
- Hokkaido UniversityJP2 papers
- International Computer Science InstituteUS2 papers
- University of California, BerkeleyUS2 papers
- Alliance for Safe KidsUS1 paper
- Arrow International (United States)US1 paper
- Artificial Intelligence in Medicine (Canada)CA1 paper
- Association for Computing MachineryUS1 paper
Showing 2019Show all
2 papers · 1 filter
cs.CV2019
DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction
Andreas Kuhn, Christian Sormann, Mattia Rossi +2
Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and…
cs.LG2019★ 49 cited
Mixed Precision DNNs: All you need is a good parametrization
Stefan Uhlich, Lukas Mauch, Fabien Cardinaux +5
Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precisio…