A PyTorch implementation of the paper "Neural Image Representations for Multi-Image Fusion and Layer Separation".
- Our code is implemented on Jupyter notebook.
- Download data, and unzip the file under the root. e.g.
~/nir/data
./visualization.ipynb
Visualization of learned canonical view in neural image representations../moire_removal.ipynb
,./obstruction_removal.ipynb
,./rain_removal.ipynb
Moire removal, obstruction removal (reflection, fence), rain removal
Please cite our paper when you use this code.
@inproceedings{nam2022neural,
title={Neural Image Representations for Multi-Image Fusion and Layer Separation},
author={Nam, Seonghyeon and Brubaker, Marcus A and Brown, Michael S},
booktitle={European Conference on Computer Vision (ECCV)},
year={2022}
}
Our implementation is based on the official code of SIREN: https://github.com/vsitzmann/siren
Please contact snam0331 AT gmail.com if you have any question about this work.