Statistical analysis of sample values to approximate the final pixel value

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

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

License

The MIT license