Statistical analysis of sample values to approximate the final pixel value

Jérôme BUISINE 752cd0902e Merge branch 'release/v0.0.6'		преди 4 години
models_info	87b8d18661 Write Keras result script	преди 5 години
modules	87b8d18661 Write Keras result script	преди 5 години
notebooks	87b8d18661 Write Keras result script	преди 5 години
.gitignore	787d73d8f8 Scripts updates	преди 5 години
LICENSE	d0ebc63822 Update of documentation	преди 4 години
README.md	d0ebc63822 Update of documentation	преди 4 години
analyse.R	6b7c5d854b First project version; Add of dataset generation; Run script;	преди 5 години
compare_images.py	44a461faff First keras model version; Reconstruction for keras model available	преди 5 години
generate_data.sh	cccee3b412 Update of Keras scripts	преди 5 години
make_dataset.py	44a461faff First keras model version; Reconstruction for keras model available	преди 5 години
reconstruct.py	787d73d8f8 Scripts updates	преди 5 години
reconstruct_keras.py	44a461faff First keras model version; Reconstruction for keras model available	преди 5 години
reconstruct_scene_mean.py	44a461faff First keras model version; Reconstruction for keras model available	преди 5 години
run.sh	87b8d18661 Write Keras result script	преди 5 години
run_keras.sh	87b8d18661 Write Keras result script	преди 5 години
train_model.py	44a461faff First keras model version; Reconstruction for keras model available	преди 5 години
train_model_keras.py	87b8d18661 Write Keras result script	преди 5 години
write_result_keras.py	1ecca35a5f Update of write python script	преди 4 години

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