R
Radomir Mech
Researcher at Adobe Systems
Publications - 130
Citations - 4242
Radomir Mech is an academic researcher from Adobe Systems. The author has contributed to research in topics: Rendering (computer graphics) & Polygon mesh. The author has an hindex of 28, co-authored 125 publications receiving 3398 citations. Previous affiliations of Radomir Mech include Soka Gakkai International & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Minimum Barrier Salient Object Detection at 80 FPS
TL;DR: A technique based on color whitening is proposed to extend the salient object detection method to leverage the appearance-based backgroundness cue, which further improves the performance, while still being one order of magnitude faster than all the other leading methods.
Posted Content
Photo Aesthetics Ranking Network with Attributes and Content Adaptation
TL;DR: This work proposes to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function.
Proceedings ArticleDOI
Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation
TL;DR: The proposed deep multi-patch aggregation network integrates shared feature learning and aggregation function learning into a unified framework and significantly outperformed the state of the art in all three applications.
Proceedings Article
DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
TL;DR: DISN as mentioned in this paper predicts the projected location for each 3D point on the 2D image and extracts local features from the image feature maps, which significantly improves the accuracy of the signed distance field prediction, especially for the detail-rich areas.
Book ChapterDOI
Photo Aesthetics Ranking Network with Attributes and Content Adaptation
TL;DR: In this paper, a deep convolutional neural network is proposed to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function. But this method is not suitable for image aesthetics analysis.