Heat Kernel Textures (HKTex) received the Best Paper Award at #ECCV2026. UV-mapping anchors 3D texturing to the past. Inspired by 3DGS, we rethink textures using heat kernels and NO splatting! https://circle-group.github.io/research/HeatKernelTextures/…

Heat Kernel Textures

Source: https://circle-group.github.io/research/HeatKernelTextures/ AI Generated Podcast:

Your browser does not support the audio element.

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.

HKTex

**Heat Kernel Textures (HKTex)**is an intrinsic, UV-free texture representation where anisotropic heat kernels act as geodesic equivalents to Gaussians that natively conform to mesh geometry. Given a mesh, a set of known cameras, and an initialisation of our heat kernels, we continuously evaluate our representation, and render it differentiably with a Mitsuba based ray tracer. Rendered pixels are compared with the corresponding pixels in the mutliview GT images. Our method can also fit existing UV textures by directly evaluating the texture at arbitrary surface locations and comparing against corresponding UV values. The loss is then backpropagated to update the shape parameters of our kernels as well as their positions which are forced to remain on the surface.

Kernel Modulation

Each heat kernel is defined directly on the surface and parametrised by its source position, diffusion angle and anisotropy (controlling orientation and stretch), scale, sharpness, and RGB colour.

Optimization & Density Control

Kernel positions are updated along the surface using Riemannian Gradient Descent with momentum (made possible only thanks todigeo). In tandem, manifold-aware controllers prune inactive kernels and dynamically densify under-reconstructed regions by cloning or splitting kernels along their principal axes on the manifold.

Results

Fitting Existing UV-Textures

Simultaneous multi-view rotation and material rendering across all benchmark shapes fitted from standard UV maps. Use thesliderto rotate all objects, or click thematerial buttonsto switch materials.

0°60°120°180°240°300°

Multi-View Inverse Rendering

Novel view synthesis and material appearance decomposition optimized directly from multi-view image observations. Use thesliderto rotate all objects, or click thematerial buttonsto switch materials.

0°60°120°180°240°300°

BibTeX

@inproceedings{foti2026hktex,
    author    = {Foti, Simone and Korkmaz, Caner and Zafeiriou, Stefanos and Birdal, Tolga},
    title     = {Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat},
    booktitle = {Computer Vision -- ECCV 2026},
    year      = {2026},
    publisher = {Springer Nature Switzerland},
    pages     = {306--323},
    doi       = {10.1007/978-3-032-37595-7_17},
}