H
Hiroshi Ishikawa
Researcher at Waseda University
Publications - 163
Citations - 7282
Hiroshi Ishikawa is an academic researcher from Waseda University. The author has contributed to research in topics: Semiconductor laser theory & Quantum dot. The author has an hindex of 36, co-authored 162 publications receiving 6190 citations. Previous affiliations of Hiroshi Ishikawa include Nagoya City University & New York University.
Papers
More filters
Journal ArticleDOI
Globally and locally consistent image completion
TL;DR: This work presents a novel approach for image completion that results in images that are both locally and globally consistent, with a fully-convolutional neural network that can complete images of arbitrary resolutions by filling-in missing regions of any shape.
Journal ArticleDOI
Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification
TL;DR: A novel technique to automatically colorize grayscale images that combines both global priors and local image features and can process images of any resolution, unlike most existing approaches based on CNN.
Journal ArticleDOI
Exact optimization for Markov random fields with convex priors
TL;DR: A method to solve exactly a first order Markov random field optimization problem in more generality than was previously possible is introduced, which maps the problem into a minimum-cut problem for a directed graph, for which a globally optimal solution can be found in polynomial time.
Book ChapterDOI
Occlusions, Discontinuities, and Epipolar Lines in Stereo
Hiroshi Ishikawa,Davi Geiger +1 more
TL;DR: A new approach to compute the disparity map by solving a global optimization problem that models occlusions, discontinuities, and epipolar-line interactions is presented.
Journal ArticleDOI
Globally optimal regions and boundaries as minimum ratio weight cycles
Ian H. Jermyn,Hiroshi Ishikawa +1 more
TL;DR: A new form of energy functional is described that is defined on the space of boundaries in the image domain and can incorporate very general combinations of modeling information both from the boundary and from the interior of the region.