Stop Thinking, Just Do!

Sung-Soo Kim's Blog

Geometric Detail Transfer


4 April 2017

Article Source

Geometric Detail Transfer

The paper “Learning Detail Transfer based on Geometric Features” is available here:

The story of our recent software and hardware overhaul:


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, and 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.

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).

comments powered by Disqus