S-Aware-network (AAAI'2023)

Introduction

This is an implementation of the following paper.

Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning. AAAI Conference on Artificial Intelligence, (AAAI'2023)

[Paper] [Poster] [Slides]

Datasets

Intrinsic Image Decomposition

1.IIW_Download OR IIW

2.MIT OR MIT

3.MPI-Sintel

4.ShapeNet (https://github.com/JannerM/intrinsics-network)

Shadow Removal

1.SRD (train BaiduNetdisk and test).

2.USR

Specularity/highlight Removal

1.Specularity separation

2.[ShapeNet]

Renjiao Yi, Ping Tan and Stephen Lin, "Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation", AAAI 2020.

Specular-Free Loss

Get the following Figure 6 in the main paper,

demo_spfree_release.m

License

The code and models in this repository are licensed under the MIT License for academic and other non-commercial uses.
For commercial use of the code and models, separate commercial licensing is available. Please contact:

• Yeying Jin (jinyeying@u.nus.edu)
• Robby T. Tan (tanrobby@gmail.com)
• Jonathan Tan (jonathan_tano@nus.edu.sg)

Citation

If this work is useful for your research, please cite our paper.

@inproceedings{jin2023estimating,
  title={Estimating reflectance layer from a single image: Integrating reflectance guidance and shadow/specular aware learning},
  author={Jin, Yeying and Li, Ruoteng and Yang, Wenhan and Tan, Robby T},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={37},
  number={1},
  pages={1069--1077},
  year={2023}
}