Heat kernel textures improve 3D surface details without UV mapping
Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat
Computer Vision and Pattern RecognitionGraphicsMachine Learning
Summary
People often use UV mapping to put images on 3D objects, but this can cause problems like wasted space, seams, and distortions. To fix these issues, the authors created heat kernel textures that place color details directly on the 3D surface without a flat map. Their method uses math from geometry to spread colors like soft blobs shaped by the surface itself. This approach also uses less memory and works well with realistic lighting in 3D scenes. It can create textures from photos or existing images and is ready to use with common rendering tools.
3D Gaussian splattingUV mappingHeat kernelGeodesic distanceTriangular meshDiscrete Riemannian geometryTexture mappingPhysically based renderingMulti-view imagesMemory footprint
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.