Heat kernel textures improve 3D surface texturing without UV mapping
Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat
Computer Vision and Pattern RecognitionGraphicsMachine Learning
Summary
Texturing 3D objects usually involves flattening their surfaces into 2D maps, which can waste space and cause problems like seams and distortions. The authors propose Heat Kernel Textures (HKTex), a way to apply textures directly on 3D surfaces using math from geometry to avoid these issues. Instead of relying on traditional UV maps, HKTex uses special heat kernel functions spread over the object’s surface, which can be optimized from images or existing textures. This approach reduces memory use and works naturally on any mesh shape without flattening.
What this means in practice
- •For 3d graphics developers: Create 3D models with textures that avoid UV mapping issues like seams and distortions, improving visual quality and reducing memory needs.
- •For game engine teams: Integrate heat kernel textures to optimize texture storage and rendering efficiency on complex 3D surfaces for real-time applications.
Authors
Simone Foti, Caner Korkmaz, Stefanos Zafeiriou, Tolga Birdal
Abstract
3D Gaussian Splatting has recently revolutionised novel view synthesis as well as many other 3D vision methods and applications. Drawing inspiration from this representation, we now rethink textures to overcome the main issues of UV mapping while considerably lowering their memory footprint. Heat Kernel Textures (HKTex) eliminate UV unwrapping as well as their persistent issues of wasted UV space, seams, distortions, vertex-duplication, and varying resolution. Grounded in discrete Riemannian geometry and intrinsically defined on any manifold surface discretised as a triangular mesh, HKTex uses anisotropic heat kernels as geodesic equivalents to Gaussians. Like our kernels, also the optimisation of their position and the adaptive densification strategies were redefined to operate on the surface of the object to be textureised. Our novel representation is also fully integrated with a physically based renderer and can be optimised either from existing textures or multi-view images. Our project page and code are available at circle-group.github.io/research/HeatKernelTextures.