Relighting Images in the Wild with a Self-Supervised Siamese Auto-Encoder

被引:6
|
作者
Liu, Yang [1 ]
Neophytou, Alexandros [2 ]
Sengupta, Sunando [2 ]
Sommerlade, Eric [2 ]
机构
[1] Univ Surrey, Guildford, Surrey, England
[2] Microsoft Corp, Reading, Berks, England
关键词
D O I
10.1109/WACV48630.2021.00008
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a self-supervised method for image relighting of single view images in the wild. The method is based on an auto-encoder which deconstructs an image into two separate encodings, relating to the scene illumination and content, respectively. In order to disentangle this embedding information without supervision, we exploit the assumption that some augmentation operations do not affect the image content and only affect the direction of the light. A novel loss function, called spherical harmonic loss, is introduced that forces the illumination embedding to convert to a spherical harmonic vector. We train our model on large-scale datasets such as Youtube 8M and CelebA. Our experiments show that our method can correctly estimate scene illumination and realistically re-light input images, without any supervision or a prior shape model. Compared to supervised methods, our approach has similar performance and avoids common lighting artifacts.
引用
下载
收藏
页码:32 / 40
页数:9
相关论文
共 50 条
  • [31] Siamese Recurrent Auto-Encoder Representation for Query-by-Example Spoken Term Detection
    Zhu, Ziwei
    Wu, Zhiyong
    Li, Runnan
    Meng, Helen
    Cai, Lianhong
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 102 - 106
  • [32] Group-based siamese self-supervised learning
    Li, Zhongnian
    Wang, Jiayu
    Geng, Qingcong
    Xu, Xinzheng
    ELECTRONIC RESEARCH ARCHIVE, 2024, 32 (08): : 4913 - 4925
  • [33] Change Detection Based on Auto-encoder Model for VHR Images
    Xu, Yuan
    Xiang, Shiming
    Huo, Chunlei
    Pan, Chunhong
    MIPPR 2013: PATTERN RECOGNITION AND COMPUTER VISION, 2013, 8919
  • [34] DEEP FEATURE EXTRACTION BASED ON SIAMESE NETWORK AND AUTO-ENCODER FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Miao, Jiajia
    Wang, Bin
    Wu, Xiaofeng
    Zhang, Liming
    Hu, Bo
    Zhang, Jian Qiu
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 397 - 400
  • [35] Semi-Supervised Auto-Encoder Graph Network for Diabetic Retinopathy Grading
    Li, Yujie
    Song, Zhang
    Kang, Sunkyoung
    Jung, Sungtae
    Kang, Wenpei
    IEEE ACCESS, 2021, 9 : 140759 - 140767
  • [36] Network Intrusion Detection Based on Supervised Adversarial Variational Auto-Encoder With Regularization
    Yang, Yanqing
    Zheng, Kangfeng
    Wu, Bin
    Yang, Yixian
    Wang, Xiujuan
    IEEE ACCESS, 2020, 8 : 42169 - 42184
  • [37] Network Intrusion Detection Based on Semi-supervised Variational Auto-Encoder
    Osada, Genki
    Omote, Kazumasa
    Nishide, Takashi
    COMPUTER SECURITY - ESORICS 2017, PT II, 2017, 10493 : 344 - 361
  • [38] Semi-Supervised Domain Adaptation with Auto-Encoder via Simultaneous Learning
    Rahman, Md Mahmudur
    Panda, Rameswar
    Alam, Mohammad Arif Ul
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 402 - 411
  • [39] Self-Supervised Variational Auto-Encoders
    Gatopoulos, Ioannis
    Tomczak, Jakub M.
    ENTROPY, 2021, 23 (06)
  • [40] Semi-Supervised Adversarial Auto-Encoder to Expedite Human Activity Recognition
    Thapa, Keshav
    Seo, Yousung
    Yang, Sung-Hyun
    Kim, Kyong
    SENSORS, 2023, 23 (02)