S
Shai Avidan
Researcher at Tel Aviv University
Publications - 153
Citations - 17052
Shai Avidan is an academic researcher from Tel Aviv University. The author has contributed to research in topics: Pixel & Computer science. The author has an hindex of 50, co-authored 138 publications receiving 15378 citations. Previous affiliations of Shai Avidan include Mitsubishi Electric Research Laboratories & Mitsubishi.
Papers
More filters
Journal ArticleDOI
Physics Based Image Deshadowing Using Local Linear Model
TL;DR: This work follows a common physical shadow formation model and learns its parameters using a deep neural network, which consists of an existing network for shadow detection, and a novel network forshadow removal.
Journal Article
How Low Can We Go? Pixel Annotation for Semantic Segmentation
TL;DR: An experiment to answer the question how many labeled pixels are needed to segment an image, without any prior knowledge, and finds that it is possible to reach the performance of a fully annotated data set using a fraction of the annotation cost.
Journal ArticleDOI
Stress-Testing LiDAR Registration
TL;DR: A method for selecting balanced registration sets, which are challenging sets of frame-pairs from LiDAR datasets, which contain a balanced representation of the different relative motions that appear in a dataset, i.e.Small and large rotations, small and large offsets in space and time, and various combinations of these.
Posted Content
Proximity Preserving Binary Code using Signed Graph-Cut
TL;DR: A binary embedding framework, called Proximity Preserving Code (PPC), which learns similarity and dissimilarity between data points to create a compact and affinity-preserving binary code, which can be used to apply fast and memory-efficient approximation to nearest-neighbor searches.