Search Results for author: Ohad Ben-Shahar

Found 9 papers, 2 papers with code

Crossing Cuts Polygonal Puzzles: Models and Solvers

no code implementations CVPR 2021 Peleg Harel, Ohad Ben-Shahar

Jigsaw puzzle solving, the problem of constructing a coherent whole from a set of non-overlapping unordered fragments, is fundamental to numerous applications, and yet most of the literature has focused thus far on less realistic puzzles whose pieces are identical squares.

Pictorial and apictorial polygonal jigsaw puzzles: The lazy caterer model, properties, and solvers

no code implementations17 Aug 2020 Peleg Harel, Ohad Ben-Shahar

Jigsaw puzzle solving, the problem of constructing a coherent whole from a set of non-overlapping unordered visual fragments, is fundamental to numerous applications and yet most of the literature of the last two decades has focused thus far on less realistic puzzles whose pieces are identical squares.

NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image

1 code implementation7 May 2020 Boaz Arad, Radu Timofte, Ohad Ben-Shahar, Yi-Tun Lin, Graham Finlayson, Shai Givati, others

This paper reviews the second challenge on spectral reconstruction from RGB images, i. e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image.

Spectral Reconstruction

Contextual Object Detection with a Few Relevant Neighbors

no code implementations15 Nov 2017 Ehud Barnea, Ohad Ben-Shahar

A natural way to improve the detection of objects is to consider the contextual constraints imposed by the detection of additional objects in a given scene.

Object object-detection +1

Exploring the Bounds of the Utility of Context for Object Detection

1 code implementation CVPR 2019 Ehud Barnea, Ohad Ben-Shahar

In this work we seek to improve our understanding of this phenomenon, in part by pursuing an opposite approach.

object-detection Object Detection

Curve Reconstruction via the Global Statistics of Natural Curves

no code implementations CVPR 2018 Ehud Barnea, Ohad Ben-Shahar

To address this practical issue we explore and exploit statistical geometrical properties of natural curves, and in particular, we show that in many cases the mean curve is scale invariant and oftentimes it is extensible.

Image Inpainting

Filter Selection for Hyperspectral Estimation

no code implementations ICCV 2017 Boaz Arad, Ohad Ben-Shahar

While recovery of hyperspectral signals from natural RGB images has been a recent subject of exploration, little to no consideration has been given to the camera response profiles used in the recovery process.

From Square Pieces to Brick Walls: The Next Challenge in Solving Jigsaw Puzzles

no code implementations ICCV 2017 Shir Gur, Ohad Ben-Shahar

Research into computational jigsaw puzzle solving, an emerging theoretical problem with numerous applications, has focused in recent years on puzzles that constitute square pieces only.

Cannot find the paper you are looking for? You can Submit a new open access paper.