PrincetonComputer SciencePIXL GroupPublications → [Berkiten et al. 2017] Local Access
Learning Detail Transfer based on Geometric Features

Computer Graphics Forum (Proc. Eurographics), April 2017

Sema Berkiten, Maciej Halber, Justin Solomon,
Chongyang Ma, Hao Li, Szymon Rusinkiewicz
Our algorithm learns combinations of geometric features that predict the spatial arrangement of details on surfaces. Left: Input (target) mesh without details. Center/Right: Details from each source mesh (blue) are synthesized on the target mesh (pink).

The visual richness of computer graphics applications is frequently limited by the difficulty of obtaining high-quality, detailed 3D models. This paper proposes a method for realistically transferring details (specifically, displacement maps) from existing high-quality 3D models to simple shapes that may be created with easy-to-learn modeling tools. Our key insight is to use metric learning to find a combination of geometric features that successfully predicts detail-map similarities on the source mesh; we use the learned feature combination to drive the detail transfer. The latter uses a variant of multi-resolution non-parametric texture synthesis, augmented by a high-frequency detail transfer step in texture space. We demonstrate that our technique can successfully transfer details among a variety of shapes including furniture and clothing.

Sema Berkiten, Maciej Halber, Justin Solomon, Chongyang Ma, Hao Li, and Szymon Rusinkiewicz.
"Learning Detail Transfer based on Geometric Features."
Computer Graphics Forum (Proc. Eurographics) 36(2), April 2017.


   author = "Sema Berkiten and Maciej Halber and Justin Solomon and Chongyang Ma and
      Hao Li and Szymon Rusinkiewicz",
   title = "Learning Detail Transfer based on Geometric Features",
   journal = "Computer Graphics Forum (Proc. Eurographics)",
   year = "2017",
   month = apr,
   volume = "36",
   number = "2"