Deep image relighting allows photo enhancement by illumination-specific retouching without human effort and so it is getting much interest lately. Most of the existing popular methods available for relighting are run-time intensive and memory inefficient. Keeping these issues in mind, we propose the use of Stacked Deep Multi-Scale Hierarchical Network, which aggregates features from each image at different scales. Our solution is differentiable and robust for translating image illumination setting from input image to target image. Additionally, we have also shown that using a multi-step training approach to this problem with two different loss functions can significantly boost performance and can achieve a high quality reconstruction of a relighted image.
@article{arxiv.2107.06125,
title = {MSR-Net: Multi-Scale Relighting Network for One-to-One Relighting},
author = {Sourya Dipta Das and Nisarg A. Shah and Saikat Dutta},
journal= {arXiv preprint arXiv:2107.06125},
year = {2021}
}
Comments
Workshop on Differentiable Vision, Graphics, and Physics in Machine Learning at NeurIPS 2020. arXiv admin note: text overlap with arXiv:2102.09242