Y
Yagiz Aksoy
Researcher at ETH Zurich
Publications - 26
Citations - 676
Yagiz Aksoy is an academic researcher from ETH Zurich. The author has contributed to research in topics: Computer science & Pixel. The author has an hindex of 9, co-authored 20 publications receiving 397 citations. Previous affiliations of Yagiz Aksoy include The Walt Disney Company & Simon Fraser University.
Papers
More filters
Posted Content
Designing Effective Inter-Pixel Information Flow for Natural Image Matting
TL;DR: This work presents a novel, purely affinity-based natural image matting algorithm that relies on carefully defined pixel-to-pixel connections that enable effective use of information available in the image and the trimap and introduces color-mixture flow, which builds upon local linear embedding and effectively encapsulates the relation between different pixel opacities.
Journal ArticleDOI
Semantic soft segmentation
TL;DR: This work introduces semantic soft segments, a set of layers that correspond to semantically meaningful regions in an image with accurate soft transitions between different objects, and proposes a graph structure that embeds texture and color features from the image as well as higher-level semantic information generated by a neural network.
Proceedings ArticleDOI
Learning-Based Sampling for Natural Image Matting
TL;DR: The estimation of the layer colors through the use of deep neural networks prior to the opacity estimation is a better match for the capabilities of neural networks, and the availability of these colors substantially increase the performance of opacity estimation due to the reduced number of unknowns in the compositing equation.
Proceedings ArticleDOI
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
TL;DR: In this article, a simple depth merging network is proposed to take advantage of the duality between a consistent scene structure and high-frequency details, and a patch selection method is used to add local details to the final result.
Journal ArticleDOI
Unmixing-Based Soft Color Segmentation for Image Manipulation
TL;DR: A new method for decomposing an image into a set of soft color segments that are analogous to color layers with alpha channels that have been commonly utilized in modern image manipulation software is presented.