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
Seam carving for content-aware image resizing
Shai Avidan,Ariel Shamir +1 more
TL;DR: In this article, seam carving is used for content-aware image resizing for both reduction and expansion, where an optimal 8-connected path of pixels on a single image from top to bottom, or left to right, where optimality is defined by an image energy function.
Journal ArticleDOI
Improved seam carving for video retargeting
TL;DR: This work replaces the dynamic programming method of seam carving with graph cuts that are suitable for 3D volumes and presents a novel energy criterion that improves the visual quality of the retargeted images and videos.
Journal ArticleDOI
Sketch2Photo: internet image montage
TL;DR: A system that composes a realistic picture from a simple freehand sketch annotated with text labels, able to automatically select suitable photographs to generate a high quality composition, using a filtering scheme to exclude undesirable images.
Journal ArticleDOI
A survey on Mesh Segmentation Techniques
TL;DR: A review of the state of the art of segmentation and partitioning techniques of boundary meshes and identifies two primarily distinct types of mesh segmentation, namely part segments and surface‐patch segmentation.
Journal ArticleDOI
Consistent mesh partitioning and skeletonisation using the shape diameter function
TL;DR: This paper considers mesh partitioning and skeletonisation on a wide variety of meshes, and bases its algorithms on a volume-based shape-function called the shape-diameter-function (SDF), which remains largely oblivious to pose changes of the same object and maintains similar values in analogue parts of different objects.