Statistical analysis of sample values to approximate the final pixel value

Jérôme BUISINE be401816c8 Merge branch 'release/v0.0.9'		4 年前
generate	95cba96b9b Use of modules dependency	4 年前
modules @ d5de038bdc	95cba96b9b Use of modules dependency	4 年前
notebooks	87b8d18661 Write Keras result script	5 年前
others	95cba96b9b Use of modules dependency	4 年前
reconstruct	95cba96b9b Use of modules dependency	4 年前
.gitignore	ab86ef6206 Documentation and ignore files updates	4 年前
.gitmodules	95cba96b9b Use of modules dependency	4 年前
LICENSE	d0ebc63822 Update of documentation	4 年前
README.md	ab86ef6206 Documentation and ignore files updates	4 年前
__init__.py	beb4716c41 Add of feature choices	4 年前
compare_images.py	95cba96b9b Use of modules dependency	4 年前
custom_config.py	95cba96b9b Use of modules dependency	4 年前
features.py	95cba96b9b Use of modules dependency	4 年前
generate_data.sh	cccee3b412 Update of Keras scripts	5 年前
run.sh	95cba96b9b Use of modules dependency	4 年前
run_keras.sh	95cba96b9b Use of modules dependency	4 年前
train_model.py	018d8e801f Update of train model script	4 年前
train_model_keras.py	95cba96b9b Use of modules dependency	4 年前

Sample Analysis

Description

The aim of this project is to predict the mean pixel value from monte carlo process rendering in synthesis images using only few samples information in input for model.

Data

Data are all scenes samples information obtained during the rendering process.

For each pixel we have a list of all grey value estimated (samples).

Models

List of models tested :

Ridge Regression
SGD
SVR (with rbf kernel)

How to use

First you need to contact jerome.buisine@univ-littoral.fr in order to get datatset version. The dataset is not available with this source code.

python make_dataset.py --n 10 --each_row 8 --each_column 8

python reconstruct.py --scene Scene1 --model_path saved_models/Model1.joblib --n 10 --image_name output.png

License

The MIT license

README.md