Statistical analysis of sample values to approximate the final pixel value

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

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