Statistical analysis of sample values to approximate the final pixel value

Jérôme BUISINE afac4acc1e Merge branch 'release/v0.0.7'		vor 4 Jahren
models_info	beb4716c41 Add of feature choices	vor 4 Jahren
modules	beb4716c41 Add of feature choices	vor 4 Jahren
notebooks	87b8d18661 Write Keras result script	vor 5 Jahren
.gitignore	beb4716c41 Add of feature choices	vor 4 Jahren
LICENSE	d0ebc63822 Update of documentation	vor 4 Jahren
README.md	d0ebc63822 Update of documentation	vor 4 Jahren
__init__.py	beb4716c41 Add of feature choices	vor 4 Jahren
analyse.R	6b7c5d854b First project version; Add of dataset generation; Run script;	vor 5 Jahren
compare_images.py	44a461faff First keras model version; Reconstruction for keras model available	vor 5 Jahren
generate_data.sh	cccee3b412 Update of Keras scripts	vor 5 Jahren
make_dataset.py	beb4716c41 Add of feature choices	vor 4 Jahren
reconstruct.py	beb4716c41 Add of feature choices	vor 4 Jahren
reconstruct_keras.py	beb4716c41 Add of feature choices	vor 4 Jahren
reconstruct_scene_mean.py	44a461faff First keras model version; Reconstruction for keras model available	vor 5 Jahren
run.sh	beb4716c41 Add of feature choices	vor 4 Jahren
run_keras.sh	beb4716c41 Add of feature choices	vor 4 Jahren
train_model.py	44a461faff First keras model version; Reconstruction for keras model available	vor 5 Jahren
train_model_keras.py	87b8d18661 Write Keras result script	vor 5 Jahren
write_result_keras.py	beb4716c41 Add of feature choices	vor 4 Jahren

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