Deep Illuminator is a data augmentation tool designed for image relighting.

Overview

Deep Illuminator

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image. It has been tested with several datasets and models and has been shown to succesfully improve performance. It has a built in visualizer created with Streamlit to preview how the target image can be relit.

Example Augmentations

Usage

The simplest method to use this tool is through Docker Hub:

docker pull kartvel/deep-illuminator

Visualizer

Once you have the Deep Illuminator image run the following command to launch the visualizer:

docker run -it --rm  --gpus all \
-p 8501:8501 --entrypoint streamlit \ 
kartvel/deep-illuminator run streamlit/streamlit_app.py

You will be able to interact with it on localhost:8501. Note: If you do not have NVIDIA gpu support enabled for docker simply remove the --gpus all option.

Generating Variants

It is possible to quickly generate multiple variants for images contained in a directory by using the following command:

docker run -it --rm --gpus all \                                                                                               ─╯
-v /path/to/input/images:/app/probe_relighting/originals \
-v /path/to/save/directory:/app/probe_relighting/output \
kartvel/deep-illuminator --[options]

Options

Option Values Description
mode ['synthetic', 'mid'] Selecting the style of probes used as a relighting guide.
step int Increment for the granularity of relighted images. max mid: 24, max synthetic: 360

Buidling Docker image or running without a container

Please read the following for other options: instructions

Benchmarks

Improved performance of R2D2 for [email protected] on HPatches

Training Dataset Overall Viewpoint Illumination
COCO - Original 71.0 65.4 77.1
COCO - Augmented 72.2 (+1.7%) 65.7 (+0.4%) 79.2 (+2.7%)
VIDIT - Original 66.7 60.5 73.4
VIDIT - Augmented 69.2 (+3.8%) 60.9 (+0.6%) 78.1 (+6.4%)
Aachen - Original 69.4 64.1 75.0
Aachen - Augmented 72.6 (+4.6%) 66.1 (+3.1%) 79.6 (+6.1%)

Improved performance of R2D2 for the Long-Term Visual Localization challenge on Aachen v1.1

Training Dataset 0.25m, 2° 0.5m, 5° 5m, 10°
COCO - Original 62.3 77.0 79.5
COCO - Augmented 65.4 (+5.0%) 83.8 (+8.8%) 92.7 (+16%)
VIDIT - Original 40.8 53.4 61.3
VIDIT - Augmented 53.9 (+32%) 71.2 (+33%) 83.2(+36%)
Aachen - Original 60.7 72.8 83.8
Aachen - Augmented 63.4 (+4.4%) 81.7 (+12%) 92.1 (+9.9%)

Acknowledgment

The developpement of the VAE for the visualizer was made possible by the PyTorch-VAE repository.

Polyfoto - Create image mosaics.

Polyfoto Create image mosaics. Showcase "Before and After Science" by Brian Eno "Scott 3" by Scott Walker Installation Clone this repository to your l

Shane Drabing 149 Dec 25, 2022
Art directed cropping, useful for responsive images

Art direction sets a focal point and can be used when you need multiple copies of the same Image but also in in different proportions.

Daniel 1 Aug 16, 2022
Cat avatars for adult independent users

Cat avatars for adult independent users Samples (Natasha, wake up!) Usage Check values from https://shantichat.github.io/avacats/index.json: { "sizes"

4 Nov 05, 2021
Water marker for images.

watermarker linux users: To fix this error,please add truetype font path File "watermark.py", line 58, in module font = ImageFont.truetype("Dro

13 Oct 27, 2022
Demo of using Auto Encoder for Image Denoising

Demo of using Auto Encoder for Image Denoising

2 Aug 04, 2022
This is a python project which detects color of an image when you double click on it.

This is a python project which detects color of an image when you double click on it. You have to press ESC button to close the pop-up Image window. There are mainly two library CV2 and Pandas that a

Yashwant Kumar Singh 0 Aug 16, 2022
Image Reading, Metadata Conversion, and Image Writing for Microscopy Images in Python

AICSImageIO Image Reading, Metadata Conversion, and Image Writing for Microscopy Images in Pure Python Features Supports reading metadata and imaging

Allen Institute for Cell Science - Modeling 137 Dec 14, 2022
Convert photos to paintings with python

Convert-photos-to-paintings Before the changes After the changes Before the changes After the changes This code is written in the Python programming l

Amir Hussein Sharifnezhad 3 May 31, 2022
Make your master artistic punk avatar through machine learning world famous paintings

Master-art-punk Make your master artistic punk avatar through machine learning world famous paintings. 通过机器学习世界名画制作属于你的大师级艺术朋克头像 Nowadays, NFT is beco

蒋虎成 23 Jan 04, 2022
Program to export all new icons from the latest Fortnite patch

Assets Exporter This program allows you to generate all new icons of a patch in png! Requierements Python =3.8 (installed on your computer) If you wa

ᴅᴊʟᴏʀ3xᴢᴏ 6 Jun 24, 2022
missing-pixel-filler is a python package that, given images that may contain missing data regions (like satellite imagery with swath gaps), returns these images with the regions filled.

Missing Pixel Filler This is the official code repository for the Missing Pixel Filler by SpaceML. missing-pixel-filler is a python package that, give

SpaceML 11 Jul 19, 2022
Steganography Image/Data Injector.

Byte Steganography Image/Data Injector. For artists or people to inject their own print/data into their images. TODO Add more file formats to support.

Ori 4 Nov 16, 2022
Typesheet is a tiny Python script for creating transparent PNG spritesheets from TrueType (.ttf) fonts.

typesheet typesheet is a tiny Python script for creating transparent PNG spritesheets from TrueType (.ttf) fonts. I made it because I couldn't find an

Grayson Chao 12 Dec 23, 2022
This is the official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.

Freedom to build what you want FreeCAD is an open-source parametric 3D modeler made primarily to design real-life objects of any size. Parametric modeling allows you to easily modify your design by g

FreeCAD 12.9k Jan 07, 2023
A tool and a library for SVG path data transformations.

SVG path data transformation toolkit A tool and a library for SVG path data transformations. Currently it supports a translation and a scaling. Usage

Igor Mikushkin 2 Mar 07, 2022
MaryJane is a simple MJPEG server written in Python.

MaryJane is a simple MJPEG server written in Python.

bootrino 152 Dec 13, 2022
Magic-Square - Creates a magic square by randomly generating a list until the list happens to be a magic square

Magic-Square Creates a magic square by randomly generating a list until the list happens to be a magic square. Done as simply as possible... Frequentl

Nick 2 Jan 01, 2022
Javascript image annotation tool based on image segmentation.

JS Segment Annotator Javascript image annotation tool based on image segmentation. Label image regions with mouse. Written in vanilla Javascript, with

Kota Yamaguchi 513 Nov 15, 2022
Tools for making image cutouts from sets of TESS full frame images

Cutout tools for astronomical images Astrocut provides tools for making cutouts from sets of astronomical images with shared footprints. It is under a

Space Telescope Science Institute 20 Dec 16, 2022
👾 Python project to help you convert any image into a pixel art.

👾 Pixel Art Generator Python project to help you convert any image into a pixel art. ⚙️ Developer's Guide Things you need to get started with this co

Atul Anand 6 Dec 14, 2022