A
Ariel Shamir
Researcher at Interdisciplinary Center Herzliya
Publications - 146
Citations - 11091
Ariel Shamir is an academic researcher from Interdisciplinary Center Herzliya. The author has contributed to research in topics: Object (computer science) & Context (language use). The author has an hindex of 48, co-authored 146 publications receiving 10116 citations. Previous affiliations of Ariel Shamir include University of Texas at Austin & Mitsubishi Electric.
Papers
More filters
Proceedings ArticleDOI
Adult2child: Motion Style Transfer using CycleGANs
TL;DR: It is proposed that style translation is an effective way to transform adult motion capture data to the style of child motion, and results show that the translated adult motions are recognized as child motions significantly more often than adult motions.
Proceedings ArticleDOI
Volumetric Michell trusses for parametric design & fabrication
Rahul Arora,Alec Jacobson,Timothy R. Langlois,Yijiang Huang,Caitlin Mueller,Wojciech Matusik,Ariel Shamir,Karan Singh,David I. W. Levin +8 more
TL;DR: The first algorithm for designing volumetric Michell Trusses is presented, which uses a parametrization-based approach to generate trusses made of structural elements aligned with the primary direction of an object's stress field that exhibit high strength-to-weight ratio while also being parametrically editable.
Journal ArticleDOI
Deep Portrait Image Completion and Extrapolation
TL;DR: The proposed general learning framework enables new portrait image editing applications such as occlusion removal and portrait extrapolation, and is evaluated on publicly-available portrait image datasets, and outperforms other state-of-the-art general image completion methods.
Proceedings ArticleDOI
Benchmarking non-photorealistic rendering of portraits
Paul L. Rosin,David Mould,Itamar Berger,John Collomosse,Yu-Kun Lai,Chuan Li,Hua Li,Ariel Shamir,Michael Wand,Tinghuai Wang,Holger Winnemöller +10 more
TL;DR: It is found that the existing methods are generally effective on this new image set, demonstrating that level one of the benchmark is tractable; challenges remain at level two.
Proceedings ArticleDOI
Feature-space analysis of unstructured meshes
TL;DR: This work provides a novel approach for the analysis of unstructured meshes using feature-space clustering and feature-detection, and is shown to be useful for feature-extraction, for data exploration and partitioning.