Princeton > CS Dept > PIXL > Graphics > Publications 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


Given input source meshes with high-quality surface details, shown in blue, our algorithm transfers the surface details to target meshes, shown in pink. Left / Middle: Details from the source mesh in the top row are transferred to target mesh in the bottom row. Right: Surface details are transferred from the middle seat, shown in blue, to the rest of the seats.

Abstract

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.

Citation (BibTeX)

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.

Paper
  PDF file

Links
  Project Page (includes video, supplemental material, and data)

Awards
  Best Paper Honorable Mention at Eurographics 2017