scispace - formally typeset
Proceedings ArticleDOI

Quadratic formulation of disparity estimation problem for light-field camera

Stepan Tulyakov, +2 more
- pp 2063-2067
TLDR
This paper exploits the property of the views captured by the LF camera to formulate disparity estimation problem as a quadratic energy minimization problem and allows computation of continuous disparity with subpixel accuracy.
Abstract
Newly available light-field (LF) cameras are able to capture several views of a scene simultaneously. These views typically have small parallax, and thus can be easily registered. In this paper we exploit this property of the views captured by the LF camera to formulate disparity estimation problem as a quadratic energy minimization problem. Our problem formulation has three benefits. Firstly, it allows computation of continuous disparity with subpixel accuracy. Secondly it permits recovering disparity of loosely textured objects and ensures that the disparity boundaries are aligned with the object's boundaries. And, finally, it allows finding the solution very quickly. It takes 15-20s for our non-optimized Matlab code to compute the solution for 25 × 350 × 350 input views.

read more

Citations
More filters
Book ChapterDOI

Accurate Disparity Estimation for Plenoptic Images

TL;DR: A post-processing pipeline to recover accurately the views from the raw data of a plenoptic camera such as Lytro and to estimate disparity maps in a novel way from such a light-field is proposed.
Journal ArticleDOI

An Image Rendering Pipeline for Focused Plenoptic Cameras

TL;DR: A new algorithm for microlens center calibration fully in the Fourier domain, a novel algorithm for depth map computation using a stereo focal stack, and a depth-based rendering algorithm that is able to refocus at a particular depth or to create all-in-focus images are proposed.

Learning stereo reconstruction with deep neural networks

TL;DR: Dans ce travail, nous abordons ces deux aspects en introduisant une architecture de réseau innovatrice avec un goulot dans the représentation, capable of traiter de grandes images en utilisant plus de contexte, and un estimateur qui rend le Réseau moins sensible aux ambiguïtés dans les correspondances stéréo.
Dissertation

Light Field Editing and Rendering

Matthieu Hog
TL;DR: A new graph-based pixel-wise segmentation method that, from a sparse set of user input, segments simultaneously all the views of a light field in interactive time is proposed and an automatic light field over-segmenting approach that makes use of GPUs computational power is proposed.
Patent

Method and apparatus for estimating depth of unfocused plenoptic data

TL;DR: In this paper, the authors proposed a method for estimating the depth of the unfocused plenoptic data by a disparity estimation without considering the determined pixels, which can prevent any disparity estimation method to spend time on estimating disparities for pixels that are in focus, or pixels that belong to homogeneous areas of the scene.
References
More filters
Proceedings Article

An iterative image registration technique with an application to stereo vision

TL;DR: In this paper, the spatial intensity gradient of the images is used to find a good match using a type of Newton-Raphson iteration, which can be generalized to handle rotation, scaling and shearing.
Journal ArticleDOI

A tutorial on spectral clustering

TL;DR: In this article, the authors present the most common spectral clustering algorithms, and derive those algorithms from scratch by several different approaches, and discuss the advantages and disadvantages of these algorithms.

Light field photography with a hand-held plenoptic camera

TL;DR: The plenoptic camera as mentioned in this paper uses a microlens array between the sensor and the main lens to measure the total amount of light deposited at that location, but how much light arrives along each ray.
Journal ArticleDOI

Single lens stereo with a plenoptic camera

TL;DR: The authors describe a camera for performing single lens stereo analysis, which incorporates a single main lens along with a lenticular array placed at the sensor plane and extracts information about both horizontal and vertical parallax, which improves the reliability of the depth estimates.
Proceedings ArticleDOI

The focused plenoptic camera

TL;DR: This paper presents a new approach to lightfield capture and image rendering that interprets the microlens array as an imaging system focused on the focal plane of the main camera lens, allowing for high resolution images that meet the expectations of modern photographers.
Related Papers (5)