Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up

Implementation of a CVPR2020 paper using Plenpy for the 15-663 Computational Photography course at Carnegie Mellon University

License

NotificationsYou must be signed in to change notification settings

themathgeek13/plenpy

Repository files navigation

One-Shot to Vertigo: Novel View Synthesis using Light Field Cameras

This final project was done as part of the 15-663 Fall 2020 course on Computational Photography taught by Prof. Ioannis Gkioulekas at Carnegie Mellon University. This project implements the paperThe ”Vertigo Effect” on Your Smartphone: Dolly zoom via single shot view synthesis. It also extends this by using light field cameras, with the help of the plenpy library. The results and implementation details are provided in the PDF.

The rest of this README is retained as is from plenpy.


plenpy - A plenoptic processing library for Python.

build statuscoverage reportPyPIPyPIPyPI

This is a Python package to calibrate, process and analyse(hyperspectral) light field images as well as (hyper)spectral imagesfrom either real cameras (e.g. Lytro) or synthetic/rendered images.

Note: The package is still undergoing API altering changes with each minor release.

License and Usage

This software is licensed under the GNU GPLv3 license (see below).

If you use this software in your scientific research, please citeour paper:

@Article{Schambach2020,  author  = {Schambach, Maximilian and Puente León, Fernando},  title   = {Microlens array grid estimation, light field decoding, and calibration},  journal = {IEEE Transactions on Computational Imaging},  volume  = {6},  pages   = {591--603},  year    = {2020},  doi     = {10.1109/TCI.2020.2964257},}

Quick Start

Have a look at ourUser Documentationfor notes on usage and some examples to get you started.

For a quick tryout of plenpy, you can use our latestDocker Image.

Installation

You can installplenpy directly from PyPi viapip:

$ pip install plenpy

That's it!

Dependencies

Plenpy requirespython >= 3.6 as it relies on Python syntax that hasbeen introduced in Python 3.6 such as f-strings or type hinting.Plenpy is currently tested on Python 3.6, 3.7, and 3.8.

The package dependencies are resolved automatically upon installation usingpip.For development and testing dependencies, see therequirements.txt file.The package dependencies are stated insetup.py.

Manual Installation on Unix / Linux / macOS

If you want to install from source, the installation usingmake is straightforward and installsplenpy and its runtime dependencies automatically.Ifmake is not available, or if you are running Windows, see below.

Caution: A system wide installation usingsudo is easy and possible butdiscouraged. Installing in a environment is recommended.

To installplenpy, first clone the project's git repository toa location of your desire and change directory to the project:

$ cd <path-to-plenpy>/$ git clone git@gitlab.com:iiit-public/plenpy.git$ cd plenpy

Then, install the library via:

$ make

Or, to have an editable install of plenpy, using

$ make editable

If no errors occur, you can check if the installation was successfulby running the unit tests:

$ make test

That's it! The package should now be available.

Manual Installation on Windows

Ifmake is not available on your system, the installation viapipis also straightforward. Instead of invokingmake,install by calling (e.g. from the Anaconda prompt)

$ pip install -r requirements.txt .

Please note the. at the end, referring to the current folder<path-to-plenpy>/plenpy.

Testing

You can manually run the tests usingpytest:

$ pytest <path-to-plenpy>/test/

Uninstallation

Uninstallplenpy using

$ pip uninstall plenpy

Documentation

The documentation can be foundhere.

You can also build the documentation yourself:

Dependencies and Building

The documentation is build usingSphinx.To install all necessary dependencies for the documentation, run

$ cd <path-to-plenpyr>$ make$ pip install -r docs/requirements.txt$ cd docs$ sphinx-apidoc -f -o ./ ../plenpy/$ make html

This will create the fullplenpy documentation in thedocs/_build/html folder.

Contribute

If you are interested in contributing toplenpy, feel free to create an issue orfork the project and submit a merge request. As this project is still undergoingrestructuring and extension, help is always welcome!

For Programmers

Please stick to thePEP 8 Python coding styleguide.

The docstring coding style of the reStructuredText follows thegoogledoc style.

License

Copyright (C) 2018-2020 The Plenpy Authors

This program is free software: you can redistribute it and/or modifyit under the terms of the GNU General Public License as published bythe Free Software Foundation, either version 3 of the License, or(at your option) any later version.

This program is distributed in the hope that it will be useful,but WITHOUT ANY WARRANTY; without even the implied warranty ofMERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See theGNU General Public License for more details.

You should have received a copy of the GNU General Public Licensealong with this program. If not, seehttps://www.gnu.org/licenses/.

About

Implementation of a CVPR2020 paper using Plenpy for the 15-663 Computational Photography course at Carnegie Mellon University

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages


[8]ページ先頭

©2009-2025 Movatter.jp