no code implementations • ECCV 2020 • Leo F. Isikdogan, Bhavin V. Nayak, Chyuan-Tyng Wu, Joao Peralta Moreira, Sushma Rao, Gilad Michael
The hardware implementation of SemifreddoNets provides up to an order of magnitude reduction in silicon area and power consumption as compared to their equivalent implementation on a general-purpose accelerator.
no code implementations • 2 Jan 2020 • Masayoshi Asama, Leo F. Isikdogan, Sushma Rao, Bhavin V. Nayak, Gilad Michael
We use a fully trainable, fixed-topology neural network to build a model that can perform a wide variety of image processing tasks.
no code implementations • 14 Nov 2019 • Chyuan-Tyng Wu, Leo F. Isikdogan, Sushma Rao, Bhavin Nayak, Timo Gerasimow, Aleksandar Sutic, Liron Ain-kedem, Gilad Michael
However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications.
no code implementations • 12 Jun 2019 • Leo F. Isikdogan, Timo Gerasimow, Gilad Michael
We propose an eye contact correction model that restores the eye contact regardless of the relative position of the camera and display.