Inicio Explorar Ayuda
Iniciar sesión
Prise3D
/
Thesis-SampleAnalysis
2
0
Fork 0
Archivos Incidencias 0 Pull Requests 0 Wiki

Statistical analysis of sample values to approximate the final pixel value

Árbol: ebdd1786e0
Ramas Etiquetas
Thesis-Sampl...
ZIP TAR.GZ
Jérôme BUISINE ebdd1786e0 Merge branch 'release/v0.0.5' hace 5 años
models_info 87b8d18661 Write Keras result script hace 5 años
modules 87b8d18661 Write Keras result script hace 5 años
notebooks 87b8d18661 Write Keras result script hace 5 años
.gitignore 787d73d8f8 Scripts updates hace 5 años
README.md 066fc2b99b Fix folder list issue; Add README; hace 5 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 44a461faff First keras model version; Reconstruction for keras model available hace 5 años
reconstruct.py 787d73d8f8 Scripts updates hace 5 años
reconstruct_keras.py 44a461faff First keras model version; Reconstruction for keras model available hace 5 años
reconstruct_scene_mean.py 44a461faff First keras model version; Reconstruction for keras model available hace 5 años
run.sh 87b8d18661 Write Keras result script hace 5 años
run_keras.sh 87b8d18661 Write Keras result script hace 5 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 87b8d18661 Write Keras result script hace 5 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