Statistical analysis of sample values to approximate the final pixel value

Jérôme BUISINE 8a37c3d0b9 Merge tag 'v0.0.4' into develop 5 jaren geleden
modules cccee3b412 Update of Keras scripts 5 jaren geleden
.gitignore 787d73d8f8 Scripts updates 5 jaren geleden
README.md 066fc2b99b Fix folder list issue; Add README; 5 jaren geleden
analyse.R 6b7c5d854b First project version; Add of dataset generation; Run script; 5 jaren geleden
compare_images.py 44a461faff First keras model version; Reconstruction for keras model available 5 jaren geleden
generate_data.sh cccee3b412 Update of Keras scripts 5 jaren geleden
make_dataset.py 44a461faff First keras model version; Reconstruction for keras model available 5 jaren geleden
reconstruct.py 787d73d8f8 Scripts updates 5 jaren geleden
reconstruct_keras.py 44a461faff First keras model version; Reconstruction for keras model available 5 jaren geleden
reconstruct_scene_mean.py 44a461faff First keras model version; Reconstruction for keras model available 5 jaren geleden
run.sh 787d73d8f8 Scripts updates 5 jaren geleden
run_keras.sh cccee3b412 Update of Keras scripts 5 jaren geleden
train_model.py 44a461faff First keras model version; Reconstruction for keras model available 5 jaren geleden
train_model_keras.py cccee3b412 Update of Keras scripts 5 jaren geleden

README.md

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