Scene Relighting using a Single Reference Image through Material Constrained Layer Decomposition

Scene Relighting using a Single Reference Image through Material Constrained Layer Decomposition

Xin Jin1, Yannan Li1, Ningning Liu2,Xiaodong Li1, *,Quan Zhou3,4, Yulu Tian1, Shiming Ge5, *

1Beijing Electronic Science and Technology Institute, Beijing, 100070, P.R. China

2University of International Business and Economics, Beijing, 10 0029, P.R. China

3National Engineering Research Center of Communications and Netw orking, Nanjing University of Posts and Telecommunications, P.R. China

4State Key Lab. for Novel Software Technology, Nanjing University, P.R. China

5Institute of Info. Engineering, Chinese Academy of Sciences, Beijing, 100093, P.R. China

*Corresponding authors:lxd@besti.edu.cn, geshiming@iie.ac.cn

Abstract

    Image relighting is to change the illumination of an image to a target illumination effect without known the original scene geometry, material information and illumination condition. We propose a novel outdoor scene relighting method, which needs only a single reference image and is based on material constrained layer decomposition. Firstly, the material map is extracted from the input image. Then, the reference image is warped to the input image through patch match based image warping. Lastly, the input image is relighted using material constrained layer decomposition. The experimental results reveal that our method can produce similar illumination effect as that of the reference image on the input image using only a single reference image.

Gallery

scene-1

The relit results of our method. 

Paper and Slides

pdf

Xin Jin, Yannan Li, Ningning Liu, Xiaodong Li, Quan Zhou, Yulu Tian, Shiming Ge.The 2nd International Symposium on Artificial Intelligence and Robotics (ISAIR), Kitakyushu, Japan, November 25-26, 2017.

video

mp4

发表评论

电子邮件地址不会被公开。 必填项已用*标注