TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features
This provides a practical solution for maintaining visual coherence in 3D content creation, such as in game development and simulation, though it is incremental in improving texture transfer.
The paper tackles the problem of transferring semantic textures between 3D meshes by learning a volumetric texture field from a single textured mesh, achieving superior texture transfer quality and fast inference times compared to existing methods.
As 3D content creation continues to grow, transferring semantic textures between 3D meshes remains a significant challenge in computer graphics. While recent methods leverage text-to-image diffusion models for texturing, they often struggle to preserve the appearance of the source texture during texture transfer. We present \ourmethod, a novel approach that learns a volumetric texture field from a single textured mesh by mapping semantic features to surface colors. Using an efficient triplane-based architecture, our method enables semantic-aware texture transfer to a novel target mesh. Despite training on just one example, it generalizes effectively to diverse shapes within the same category. Extensive evaluation on our newly created benchmark dataset shows that \ourmethod{} achieves superior texture transfer quality and fast inference times compared to existing methods. Our approach advances single-example texture transfer, providing a practical solution for maintaining visual coherence across related 3D models in applications like game development and simulation.