M
Michaël Gharbi
Researcher at Adobe Systems
Publications - 39
Citations - 2841
Michaël Gharbi is an academic researcher from Adobe Systems. The author has contributed to research in topics: Computer science & Rendering (computer graphics). The author has an hindex of 13, co-authored 32 publications receiving 1481 citations. Previous affiliations of Michaël Gharbi include Google & Massachusetts Institute of Technology.
Papers
More filters
Journal ArticleDOI
Convolutional neural network for earthquake detection and location
TL;DR: ConvNetQuake as discussed by the authors is a scalable convolutional neural network for earthquake detection and location from a single waveform, which was applied to study the induced seismicity in Oklahoma, USA.
Journal ArticleDOI
Deep bilateral learning for real-time image enhancement
TL;DR: In this paper, a convolutional neural network is used to predict the coefficients of a locally affine model in bilateral space, which is then applied to the full-resolution image.
Journal ArticleDOI
Deep joint demosaicking and denoising
TL;DR: A new data-driven approach forDemosaicking and denoising is introduced: a deep neural network is trained on a large corpus of images instead of using hand-tuned filters and this network and training procedure outperform state-of-the-art both on noisy and noise-free data.
Journal ArticleDOI
Learning to optimize halide with tree search and random programs
Andrew Adams,Karima Ma,Luke Anderson,Riyadh Baghdadi,Tzu-Mao Li,Michaël Gharbi,Benoit Steiner,Steven Johnson,Kayvon Fatahalian,Frédo Durand,Jonathan Ragan-Kelley +10 more
TL;DR: This work presents a new algorithm to automatically schedule Halide programs for high-performance image processing and deep learning that produces schedules which are on average almost twice as fast as the existing Halide autoscheduler without autotuning, or more than two as fast with, and is the first automatic scheduling algorithm to significantly outperform human experts on average.
Journal ArticleDOI
Deep Bilateral Learning for Real-Time Image Enhancement
TL;DR: In this article, a convolutional neural network is used to predict the coefficients of a locally affine model in bilateral space, which is then applied to the full-resolution image.