arXiv Machine Learning
Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Sep 15
Accelerating HKTex without Mesh Eigensystems: Local Unfolding and Randomized Thermal Features
arXiv:2609.14105v1 Announce Type: new Abstract: Heat Kernel Textures (HKTex) represent surface appearance with intrinsic anisotropic kernels, but evaluate them using 50 global Laplace-Beltrami eige...
arXiv Computer Vision
Sep 22
LiteTex-GS: Fast and Lightweight Texturing for Gaussian Splatting
arXiv:2609.23380v1 Announce Type: new Abstract: Gaussian Splatting has enabled real-time novel view synthesis, but its tightly coupled geometry and appearance representation often require a large num...
arXiv AI
Sep 25
ADATEX4D: adaptive texture capacity allocation for 4D gaussian splatting
ADATEX4D introduces an adaptive texture-capacity module for deformation-based 4D Gaussian Splatting, allowing each Gaussian to carry packed RGBA triplanes whose axes grow independently based on visibility-normalized screen-space gradients and deformed local scales. The method reduces texture storage by more than half on datasets such as N3DV and PanopticSports while preserving reconstruction quality. Under fixed memory budgets, adaptive allocation improves quality over uniform texture assignment and lowers overall model and peak memory usage.
Hugging Face Trending Papers
Sep 24
ADATEX4D: adaptive texture capacity allocation for 4D gaussian splatting
ADATEX4D introduces an adaptive texture-capacity module for 4D Gaussian Splatting, allowing each Gaussian to carry packed RGBA triplanes whose axes grow independently based on visibility-normalized screen-space gradients and deformed local scales. This approach reduces texture storage by more than half while maintaining reconstruction quality, as shown in experiments on N3DV and PanopticSports. Under fixed memory budgets, adaptive allocation improves quality over uniform texture assignment and lowers overall model and peak memory usage.
arXiv AI
Jul 1
Intrinsic decomposition and editing of 3D Gaussian splats
arXiv:2606. 31637v1 Announce Type: cross Abstract: Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image editing as it enables the modification of object colors and textures without altering lighting.
arXiv Computer Vision
2d ago
Bake It Till You Make It: Ultrafast Spatial Texture-Atlas Splatting
arXiv:2607.13808v2 Announce Type: replace Abstract: Neural radiance representations in Gaussian Splatting (GS) deliver high-fidelity color detail but impose substantial rendering overhead from networ...