Content-aware texture deformation with dynamic control

Geoffrey Guingo (1, 2, 3) , Frédéric Larue (1, 2) , Basile Sauvage (1, 2) , Nicolas Lutz (1, 2) , Jean-Michel Dischler (1, 2) , Marie-Paule Cani (4)

1 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
2 UNISTRA - Université de Strasbourg
3 IMAGINE - Intuitive Modeling and Animation for Interactive Graphics & Narrative Environments
4 LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]

Textures improve the appearance of virtual scenes by mapping visual details on the surface of 3D objects. Various scenarios – such as real-time animation, interactive texture modelling, or offline post-production – require textures to be deformed in a controllable and plausible manner. We propose a novel approach to model and control texture deformations, which is easy to implement in a standard graphics pipeline. The deformation is implemented at pixel resolution as a warping in the parametric domain. The warping is controlled locally and dynamically by real-time integration along the streamlines of a pre-computed flow field. We propose a technique to pre-compute the flow field from a simple scalar map representing heterogeneous dynamic behaviors. Moreover, to manage sampling issues arising in over-stretched areas during deformation, we provide a mechanism based on re-sampling and texture synthesis. Warping may alternatively be controlled by deformation of the underlying surface, environment parameters or interactive editing, which demonstrates the versatility of our approach.

Keywords: Texturing; Deformation; Real-time; Animation; GPU

Domains: Graphics [cs.GR]

Geoffrey Guingo, Frédéric Larue, Basile Sauvage, Nicolas Lutz, Jean-Michel Dischler, et al.. Content-aware texture deformation with dynamic control. Computers and Graphics, 2020, 91, pp.95-107. ⟨10.1016/j.cag.2020.07.006⟩. ⟨hal-03183556⟩