B
Berk Kaya
Researcher at ETH Zurich
Publications - 16
Citations - 300
Berk Kaya is an academic researcher from ETH Zurich. The author has contributed to research in topics: Computer science & Hyperspectral imaging. The author has an hindex of 4, co-authored 11 publications receiving 151 citations. Previous affiliations of Berk Kaya include Middle East Technical University.
Papers
More filters
Journal ArticleDOI
EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing
TL;DR: This paper proposes a novel endmember extraction and hyperspectral unmixing scheme, so-called EndNet, that is based on a two-staged autoencoder network that is scalable for large-scale data and it can be accelerated on graphical processing units.
Posted Content
EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing
TL;DR: In this article, a two-staged autoencoder network is proposed to obtain the material spectral signatures and their fractions from hyperspectral data and a novel loss function that is composed of a Kullback-Leibler divergence term with SAD similarity and additional penalty terms to improve the sparsity of the estimates.
Proceedings ArticleDOI
Towards Spectral Estimation from a Single RGB Image in the Wild
TL;DR: In this paper, the authors use a reference spectrum as provided by a hyperspectral image camera, and propose efficient deep learning solutions for sensitivity function estimation and spectral reconstruction from a single RGB image.
Posted Content
Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces
TL;DR: This paper presents an uncalibrated deep neural network framework for the photometric stereo problem and explicitly models the concave and convex parts of a complex surface to consider the effects of interreflections in the image formation process.
Proceedings ArticleDOI
Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces
TL;DR: In this paper, the authors propose an uncalibrated neural inverse rendering approach to solve the photometric stereo problem, which first estimates the light directions from the input images and then optimizes an image reconstruction loss to calculate the surface normals, bidirectional reflectance distribution function value, and depth.