Light field editing and rendering

Matthieu Hog 1, 2
2 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : By imaging a scene from different viewpoints, a light field allows capturing a lot of information about the scene geometry. Thanks to the recent development of its acquisition devices (plenoptic camera and camera arrays mainly), light field imaging is becoming a serious alternative for 3D content capture and other related problems. The goal of this thesis is twofold. One of the main application for light field imaging is its ability to produce new views from a single capture. In a first part, we propose new image rendering techniques in two cases that deviate from the mainstream light field image rendering. We first propose a full pipeline for focused plenoptic cameras, addressing calibration, depth estimation, and image rendering. We then move to the problem of view synthesis, we seek to generate intermediates views given a set of only 4 corner views of a light field. Image editing is a common step of media production. For 2D images and videos, a lot of commercial tools exist. However, the problem is rather unexplored for light fields. In a second part, we propose new and efficient light field editing techniques. We first propose 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. Then we propose an automatic light field over-segmenting approach that makes use of GPUs computational power. This approach further decreases the computational requirement for light field segmentation and we extend the approach for light field video segmentation.
Complete list of metadatas

Cited literature [185 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02073236
Contributor : Abes Star <>
Submitted on : Tuesday, March 19, 2019 - 4:40:22 PM
Last modification on : Tuesday, February 25, 2020 - 8:08:11 AM
Long-term archiving on: Thursday, June 20, 2019 - 3:38:39 PM

File

HOG_Matthieu.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02073236, version 1

Citation

Matthieu Hog. Light field editing and rendering. Computer Vision and Pattern Recognition [cs.CV]. Université Rennes 1; Rennes 1, 2018. English. ⟨NNT : 2018REN1S064⟩. ⟨tel-02073236⟩

Share

Metrics

Record views

160

Files downloads

99