Joint Deep Estimation of Intrinsic and Dichromatic Image Decomposition

被引:0
|
作者
Ha, Jeong-Won [1 ]
Lee, Kang-Kyu [1 ]
Kim, Jong-Ok [1 ]
机构
[1] Korea Univ, Sch Elect Engn, Seoul 02841, South Korea
基金
新加坡国家研究基金会;
关键词
Reflectivity; Reflection; Lighting; Image decomposition; Image color analysis; Estimation; Surface treatment; Intrinsic image decomposition; dichromatic model; color constancy; AC light; high-speed video; HIGHLIGHT REMOVAL; REFLECTION; SEPARATION; COLOR;
D O I
10.1109/ACCESS.2023.3271114
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper proposes an image formation model that jointly combines dichromatic and intrinsic image decomposition models. The two decomposition models analyze image formation process from a different perspective, and they can be combined synergistically. It is confirmed that the proposed method performs better than the individual decomposition. The joint estimation and the study of the decomposition order ('intrinsic + dichromatic' or 'dichromatic + intrinsic') are the first attempt to the best of our knowledge. It was confirmed that the proposed 'intrinsic + dichromatic' is more optimal through experimental evaluations. We also exploit the temporal property of AC light sources, which can further improve the decomposition performance. The experimental results show that the proposed model can make an accurate image decomposition and achieve a remarkable color constancy performance.
引用
收藏
页码:41770 / 41782
页数:13
相关论文
共 50 条
  • [1] Deep Intrinsic Image Decomposition Using Joint Parallel Learning
    Yuan, Yuan
    Sheng, Bin
    Li, Ping
    Bi, Lei
    Kim, Jinman
    Wu, Enhua
    ADVANCES IN COMPUTER GRAPHICS, CGI 2019, 2019, 11542 : 336 - 341
  • [2] Intrinsic Autoencoders for Joint Deferred Neural Rendering and Intrinsic Image Decomposition
    Abu Alhaija, Hassan
    Mustikovela, Siva Karthik
    Thies, Justus
    Jampani, Varun
    Niesner, Matthias
    Geiger, Andreas
    Rother, Carsten
    2020 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2020), 2020, : 1176 - 1185
  • [3] Intrinsic decomposition with deep supervision from a single image
    Ranjit, S. Sharan
    Jaiswal, Raj K.
    JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (10) : 8647 - 8657
  • [4] Unrolled Optimization with Deep Priors for Intrinsic Image Decomposition
    Yang, Cheng
    Liu, Risheng
    Ma, Long
    Fan, Xin
    Li, Haojie
    Zhang, Miao
    2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2018,
  • [5] Deep Intrinsic Decomposition With Adversarial Learning for Hyperspectral Image Classification
    Gong, Zhiqiang
    Qi, Jiahao
    Zhong, Ping
    Zhou, Xian
    Yao, Wen
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [6] DARN: a Deep Adversarial Residual Network for Intrinsic Image Decomposition
    Lettry, Louis
    Vanhoey, Kenneth
    van Gool, Luc
    2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 1359 - 1367
  • [7] Single Scene Image Editing Based on Deep Intrinsic Decomposition
    Sha, Hao
    Liu, Yue
    Lu, Kai
    Lu, Chenguang
    Chen, Hengrun
    Wang, Yongtian
    IMAGE AND GRAPHICS (ICIG 2021), PT III, 2021, 12890 : 545 - 556
  • [8] HyperDID: Hyperspectral Intrinsic Image Decomposition With Deep Feature Embedding
    Gong, Zhiqiang
    Zhou, Xian
    Yao, Wen
    Zheng, Xiaohu
    Zhong, Ping
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 14
  • [9] A deep unfolding network based on intrinsic image decomposition for pansharpening
    Ge, Yufei
    Zhang, Xiaoli
    Huang, Bo
    Li, Xiongfei
    Ma, Siwei
    KNOWLEDGE-BASED SYSTEMS, 2025, 308
  • [10] Deep Dichromatic Guided Learning for Illuminant Estimation
    Woo, Sung-Min
    Kim, Jong-Ok
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 3623 - 3636