TL;DR
This paper introduces a deep learning framework for synthesizing geometric textures on 3D meshes by learning local geometric features, enabling texture transfer across different shapes without relying on mesh parameterization.
Contribution
It proposes a novel method that learns geometric texture statistics from local mesh patches and synthesizes textures without mesh parameterization, supporting transfer between shapes of different genus.
Findings
Enables synthesis of complex geometric textures on meshes.
Supports texture transfer between shapes of varying genus.
Operates without mesh parameterization, using local geometric features.
Abstract
Recently, deep generative adversarial networks for image generation have advanced rapidly; yet, only a small amount of research has focused on generative models for irregular structures, particularly meshes. Nonetheless, mesh generation and synthesis remains a fundamental topic in computer graphics. In this work, we propose a novel framework for synthesizing geometric textures. It learns geometric texture statistics from local neighborhoods (i.e., local triangular patches) of a single reference 3D model. It learns deep features on the faces of the input triangulation, which is used to subdivide and generate offsets across multiple scales, without parameterization of the reference or target mesh. Our network displaces mesh vertices in any direction (i.e., in the normal and tangential direction), enabling synthesis of geometric textures, which cannot be expressed by a simple 2D…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
