Home

Thomas Batard

Researcher at CIMAT                                                                                 Co-organizer of the Seminar of the Computer Science Department.     Co-organizer of the seminar ModeMat-CIMAT  on Optimization in Imaging Sciences                                                                                                                                                                                                                                                                                                                                                                                                      


De Jalisco s/n, Col. Valenciana

36023 Guanajuato

Mexico

Email: thomas.batard@cimat.mx

        

 

Research activity: Development of geometric and variational models for image processing/analysis and computer vision


 5 most representative works:

  Construction of invariants for image deblurring: T. Batard: A Class of Priors for Color Image Restoration Parametrized by Lie Groups acting on Pixel Values. SIAM Journal on Imaging  Sciences, 16(3) 2023, pp. 1235-1280 [pdf]


Variational model for denoising and deblurring using neural networks: T. Batard, G. Haro, and C. Ballester: DIP-VBTV: A Color Image  Restoration Model Combining a Deep Image Prior and a Vector Bundle Total  Variation. SIAM Journal on Imaging Sciences, 14(4) 2021, pp. 1816-1847. [pdf] [codes]

Nonlocal variational model for contrast/details enhancement: T.Batard, J. Hertrich, and G. Steidl: Variational models for color image correction inspired by visual perception and neuroscience. Journal of Mathematical Imaging and Vision, 62(9) 2020, pp. 1173-1194. [pdf]

Improving denoising methods by applying them in a moving frame: G. Ghimpeteanu, T. Batard, M. Bertalmío, and S. Levine: A Decomposition Framework for Image Denoising Algorithms. IEEE Transactions on Image Processing, 25(1) 2016, pp. 388-399. [pdf]    

Image denoising by minimizing a total variation on a vector bundle: On Covariant Derivatives and their Applications to Image  Regularization. SIAM Journal on Imaging Sciences, 7(4) 2014, pp. 2393-2422. [pdf]