Neural Style Transfer for Picture with Gradient Gram Matrix Description - Archive ouverte HAL Access content directly
Conference Papers Year :

Neural Style Transfer for Picture with Gradient Gram Matrix Description

, (1) , , , (2) , (3)
1
2
3
Heng Jin
  • Function : Author
Mengyi Zhang
  • Function : Author
Mingmin Li
  • Function : Author
Yan Wang

Abstract

Despite the high performance of neural style transfer on stylized pictures, we found that Gatys et al [1] algorithm cannot perfectly reconstruct texture style. Output stylized picture could emerge unsatisfied unexpected textures such like muddiness in local area and insufficient grain expression. Our method bases on original algorithm, adding the Gradient Gram description on style loss, aiming to strengthen texture expression and eliminate muddiness. To some extent our method lengthens the runtime, however, its output stylized pictures get higher performance on texture details, especially in the elimination of muddiness.
Not file

Dates and versions

hal-03320737 , version 1 (16-08-2021)

Identifiers

Cite

Heng Jin, Tian Wang, Mengyi Zhang, Mingmin Li, Yan Wang, et al.. Neural Style Transfer for Picture with Gradient Gram Matrix Description. 2020 39th Chinese Control Conference (CCC), Jul 2020, Shenyang, China. pp.7026-7030, ⟨10.23919/CCC50068.2020.9188652⟩. ⟨hal-03320737⟩
20 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More