Bayesian Nonparametric Intrinsic Image Decomposition

被引:0
|
作者
Chang, Jason [1 ]
Cabezas, Randi [1 ]
Fisher, John W., III [1 ]
机构
[1] MIT, CSAIL, Cambridge, MA 02139 USA
来源
关键词
Intrinsic images; Dirichlet process; Gaussian process; MCMC; SINGLE;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a generative, probabilistic model that decomposes an image into reflectance and shading components. The proposed approach uses a Dirichlet process Gaussian mixture model where the mean parameters evolve jointly according to a Gaussian process. In contrast to prior methods, we eliminate the Retinex term and adopt more general smoothness assumptions for the shading image. Markov chain Monte Carlo sampling techniques are used for inference, yielding state-of-the-art results on the MIT Intrinsic Image Dataset.
引用
收藏
页码:704 / 719
页数:16
相关论文
共 50 条
  • [41] Single Image Intrinsic Decomposition Using Transfer Learning
    Ranjit, S. Sharan
    Jaiswal, Raj K.
    ICMLC 2020: 2020 12TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND COMPUTING, 2018, : 418 - 425
  • [42] Challenges and Applications of Intrinsic Image Decomposition: A Short Review
    Diclehan Ulucan
    Oguzhan Ulucan
    Marc Ebner
    SN Computer Science, 6 (2)
  • [43] Intrinsic Image Decomposition with Step and Drift Shading Separation
    Sheng, Bin
    Li, Ping
    Jin, Yuxi
    Tan, Ping
    Lee, Tong-Yee
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2020, 26 (02) : 1332 - 1346
  • [44] Hyperspectral Intrinsic Image Decomposition With Enhanced Spatial Information
    Gu, Yanfeng
    Xie, Wen
    Li, Xian
    Jin, Xudong
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [45] 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,
  • [46] Intrinsic image decomposition as two independent deconvolution problems
    Krebs, Alexandre
    Benezeth, Yannick
    Marzani, Franck
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2020, 86
  • [47] Intrinsic Image Decomposition Using Color Invariant Edge
    Shi, Boxin
    Li, Yangxi
    Xu, Chao
    PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON IMAGE AND GRAPHICS (ICIG 2009), 2009, : 307 - 312
  • [48] Intrinsic Image Decomposition Using a Sparse Representation of Reflectance
    Shen, Li
    Yeo, Chuohao
    Hua, Binh-Son
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (12) : 2904 - 2915
  • [49] Multispectral Photometric Stereo Using Intrinsic Image Decomposition
    Hamaen, Koumei
    Miyazaki, Daisuke
    Hiura, Shinsaku
    FRONTIERS OF COMPUTER VISION, 2020, 1212 : 289 - 304
  • [50] Learning Intrinsic Image Decomposition from Watching the World
    Li, Zhengqi
    Snavely, Noah
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 9039 - 9048