Compact Neural Appearance Models for Efficient Gaussian Splatting
- Auto-discovered
Florian Hahlbohm, Jorge Condor, Linus Franke, Martin Eisemann, Marcus Magnor
Visit resource ↗Description
Compact Neural Appearance Models for Efficient Gaussian Splatting is Florian Hahlbohm, Jorge Condor, Linus Franke, Martin Eisemann, and Marcus Magnor's 2026 arXiv paper on compact view-dependent appearance for 3D Gaussian splatting.
A fused CUDA rasterizer compares spherical Voronoi, NASG, NASGabor, and SH baselines while a tiny MLP decodes latent codes, cutting third-degree SH storage from 192 to 28 bytes.
Advanced splatting readers should know differentiable Gaussian rasterization and appearance-geometry coupling.
The project page hosts PDF and a WebGL viewer for laptop and mobile GPUs.
Link last verified accessible on 2026-09-27.
Related resources
- Memory-Efficient BVHs with Merged Nodes for Hardware Ray Tracing
Memory-Efficient BVHs with Merged Nodes for Hardware Ray Tracing.
100% match · <optimization><advanced><paper><accessible><efficient><faster><last><link> - Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction augments each 3D Gaussian with a lightweight MLP that models…
100% match · <advanced><paper><accessible><gaussian><last><link><mlp><models> - Real-time Rendering with a Neural Irradiance Volume
Real-time Rendering with a Neural Irradiance Volume presents NIV, a compact neural bake of diffuse indirect lighting for real-time shading of static scenes and novel dynamic…
100% match · <shaders><advanced><paper><accessible><compact><last><link><mlp> - MeshSplatting: Differentiable Rendering with Opaque Meshes
MeshSplatting: Differentiable Rendering with Opaque Meshes presents a mesh-based novel view synthesis method by Jan Held and collaborators that jointly optimizes geometry and…
100% match · <advanced><paper><accessible><appearance><faster><gaussian><last><link> - Sample Space Partitioning and Spatiotemporal Resampling for Specular Manifold Sampling
Sample Space Partitioning and Spatiotemporal Resampling for Specular Manifold Sampling presents a Utah Graphics Lab method by Pengpei Hong, Meng Duan, Beibei Wang, Cem Yuksel,…
100% match · <advanced><paper><accessible><against><last><link><lower><per> - Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries
Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries presents a research project page by Victor Rong, Jan Held, Victor Chu, Daniel Rebain,…
100% match · <advanced><paper><accessible><against><appearance><compact><compares><gaussian> - Real-Time GPU Tree Generation
Real-Time GPU Tree Generation presents a High-Performance Graphics 2025 symposium paper by Bastian Kuth, Max Oberberger, Carsten Faber, Pirmin Pfeifer, Seyedmasih Tabaei, Dominik…
100% match · <optimization><shaders><advanced><paper><accessible><against><compact><last> - Taming optimization variance in compact neural shading networks
Taming optimization variance in compact neural shading networks.
98% match · <shaders><advanced><paper><accessible><compact><last><link><neural> - Neural Texture Compression using Hypernetworks
Neural Texture Compression using Hypernetworks.
98% match · <shaders><advanced><paper><accessible><last><link><mlp><neural> - On the Accuracy of Surface Scattering Theories
On the Accuracy of Surface Scattering Theories compares Microfacet and Generalized Harvey-Shack predictions derived from AFM and profilometer-measured metal surfaces against…
98% match · <shaders><advanced><paper><accessible><against><compares><gaussian><last> - Real-time Rendering with a Neural Irradiance Volume
Real-time Rendering with a Neural Irradiance Volume is the Eurographics 2026 paper by Arno Coomans, Giacomo Nazzaro, and coauthors from Huawei Technologies and Graz University of…
98% match · <optimization><advanced><paper><accessible><compact><last><link><neural> - Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization presents a Sakana AI paper introducing robust-kbench and an agentic pipeline that translates…
98% match · <optimization><advanced><paper><accessible><against><efficient><last><link> - DLSS 5: Generative Neural Rendering
DLSS 5: Generative Neural Rendering.
92% match · <optimization><shaders><advanced><paper><accessible><appearance><last><link> - Dual Contouring of Signed Distance Data
Dual Contouring of Signed Distance Data is a SIGGRAPH 2026 paper with a Columbia Graphics project page linking the PDF, source, and talk materials.
92% match · <advanced><paper><accessible><against><last><link><models><per> - Forget Superresolution, Sample Adaptively (when Path Tracing)
Forget Superresolution, Sample Adaptively (when Path Tracing) presents an MPI for Informatics paper by Martin Bálint, Corentin Salaün, Hans-Peter Seidel, and Karol Myszkowski on…
92% match · <optimization><shaders><advanced><paper><accessible><last><link><neural> - Practically Utilizing Neural Networks in CPU-based Production Rendering
Practically Utilizing Neural Networks in CPU-based Production Rendering presents a Journal of Computer Graphics Techniques paper by Steve Bako, Ryusuke Villemin, and Magnus…
85% match · <optimization><advanced><paper><accessible><last><link><neural><per> - Jackknife Transmittance and MIS Weight Estimation
Jackknife Transmittance and MIS Weight Estimation is a SIGGRAPH Asia 2025 paper by Christoph Peters, published in ACM Transactions on Graphics and summarized on the Moments in…
85% match · <shaders><advanced><paper><accessible><compact><last><link><lower> - Derivatives of Spherical Harmonics
Derivatives of Spherical Harmonics presents a High-Performance Graphics 2025 poster by Christoph Peters with formulas for partial derivatives of any order of the spherical…
85% match · <shaders><advanced><paper><accessible><harmonics><last><link><spherical> - Adaptive Tetrahedral Grids for Volumetric Path-Tracing
Adaptive Tetrahedral Grids for Volumetric Path-Tracing presents a SIGGRAPH Talks 2025 publication by Anis Benyoub and Jonathan Dupuy of Intel Corporation on the GGX Research…
85% match · <optimization><advanced><paper><accessible><last><link><per><reporting> - Real-time Image-based Lighting of Glints
Real-time Image-based Lighting of Glints.
85% match · <shaders><advanced><paper><accessible><gaussian><last><link><per>