Removing camera shake from a single photograph

被引:1571
|
作者
Fergus, Rob [1 ]
Singh, Barun
Hertzmann, Aaron
Roweis, Sam T.
Freeman, William T.
机构
[1] MIT, CSAIL, Cambridge, MA 02139 USA
[2] Univ Toronto, Toronto, ON, Canada
来源
ACM TRANSACTIONS ON GRAPHICS | 2006年 / 25卷 / 03期
关键词
camera shake; blind image deconvolution; variational learning; natural image statistics;
D O I
10.1145/1141911.1141956
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Camera shake during exposure leads to objectionable image blur and ruins many photographs. Conventional blind deconvolution methods typically assume frequency-domain constraints on images, or overly simplified parametric forms for the motion path during camera shake. Real camera motions can follow convoluted paths, and a spatial domain prior can better maintain visually salient image characteristics. We introduce a method to remove the effects of camera shake from seriously blurred images. The method assumes a uniform camera blur over the image and negligible in-plane camera rotation. In order to estimate the blur from the camera shake, the user must specify an image region without saturation effects. We show results for a variety of digital photographs taken from personal photo collections.
引用
收藏
页码:787 / 794
页数:8
相关论文
共 50 条
  • [1] REMOVING CAMERA FINGERPRINT TO DISGUISE PHOTOGRAPH SOURCE
    Zeng, Hui
    Chen, Jiansheng
    Kang, Xiangui
    Zeng, Wenjun
    2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 1687 - 1691
  • [2] Enhancing Bayesian Estimators for Removing Camera Shake
    Wang, C.
    Yue, Y.
    Dong, F.
    Tao, Y.
    Ma, X.
    Clapworthy, G.
    Ye, X.
    COMPUTER GRAPHICS FORUM, 2013, 32 (06) : 113 - 125
  • [3] Removing Camera Shake via Weighted Fourier Burst Accumulation
    Delbracio, Mauricio
    Sapiro, Guillermo
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (11) : 3293 - 3307
  • [4] Burst Deblurring: Removing Camera Shake Through Fourier Burst Accumulation
    Delbracio, Mauricio
    Sapiro, Guilermo
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 2385 - 2393
  • [5] Removing Non-uniform Camera Shake Using Blind Motion Deblurring
    Kim, Jinok
    Oh, Jongsuk
    Park, Rae-Hong
    2016 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2016,
  • [6] Joint Depth Estimation and Camera Shake Removal from Single Blurry Image
    Hu, Zhe
    Xu, Li
    Yang, Ming-Hsuan
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 2893 - 2900
  • [7] Digital Multi-Focusing From a Single Photograph Taken With an Uncalibrated Conventional Camera
    Cao, Yang
    Fang, Shuai
    Wang, Zengfu
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (09) : 3703 - 3714
  • [8] From phenomena to photographic concepts. The camera of Pandora: the photograph after the photograph
    Davila Lorenzana, Liliana
    INTERVENCION-REVISTA INTERNACIONAL DE CONSERVACION RESTAURACION Y MUSEOLOGIA, 2013, 4 (08): : 69 - 71
  • [9] GONIOMETRY FROM A SINGLE PHOTOGRAPH
    FILIPOV, AF
    DOKLADI NA BOLGARSKATA AKADEMIYA NA NAUKITE, 1985, 38 (05): : 599 - 602
  • [10] Modeling of Clouds from a Single Photograph
    Dobashi, Yoshinori
    Shinzo, Yusuke
    Yamamoto, Tsuyoshi
    COMPUTER GRAPHICS FORUM, 2010, 29 (07) : 2083 - 2090