Skip to content

AAAI22, Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning

Notifications You must be signed in to change notification settings

VIML-CVDL/S-Aware-network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 

Repository files navigation

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 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

Citation

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

@article{jin2022estimating,
  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},
  journal={arXiv preprint arXiv:2211.14751},
  year={2022}
}

About

AAAI22, Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • HTML 68.1%
  • Jupyter Notebook 31.8%
  • MATLAB 0.1%