Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
2026-04-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceGraphicsMachine Learning
AI summaryⓘ
The authors address a challenge in 3D view synthesis methods that use simple shapes (primitives) which struggle to capture fine details. They introduce Neural Harmonic Textures, which attach special latent features around each primitive and blend them using math inspired by Fourier analysis. This approach allows more detailed and efficient rendering of new views in real time, combining advantages of both primitive-based and neural-field methods. Their technique works well with existing systems and can also be applied to 2D images and semantic reconstructions.
3D Gaussian Splattingprimitive-based methodsnovel-view synthesisneural fieldslatent featuresFourier analysisalpha blendingharmonic componentsdeferred neural decodingsemantic reconstruction
Authors
Jorge Condor, Nicolas Moenne-Loccoz, Merlin Nimier-David, Piotr Didyk, Zan Gojcic, Qi Wu
Abstract
Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compared to neural fields, these representations are more flexible, adaptive, and scale better to large scenes. However, the limited expressivity of individual primitives makes modeling high-frequency detail challenging. We introduce Neural Harmonic Textures, a neural representation approach that anchors latent feature vectors on a virtual scaffold surrounding each primitive. These features are interpolated within the primitive at ray intersection points. Inspired by Fourier analysis, we apply periodic activations to the interpolated features, turning alpha blending into a weighted sum of harmonic components. The resulting signal is then decoded in a single deferred pass using a small neural network, significantly reducing computational cost. Neural Harmonic Textures yield state-of-the-art results in real-time novel view synthesis while bridging the gap between primitive- and neural-field-based reconstruction. Our method integrates seamlessly into existing primitive-based pipelines such as 3DGUT, Triangle Splatting, and 2DGS. We further demonstrate its generality with applications to 2D image fitting and semantic reconstruction.