AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction

Jorge Condor, Nicolas Moënne-Loccoz, Merlin Nimier-David, Piotr Didyk, Zan Gojcic, Qi Wu

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace spherical harmonics appearance with Neural Harmonic Textures3DGUT-MCMC · MipNeRF360 (standardized, 1M primitives)PSNR: 27.93 -> 28.46Improved
replace Spherical Voronoi appearance with Neural Harmonic Textures3DGUT-MCMC · Tanks & Temples (standardized)PSNR: 24.18 -> 24.79Improved
add NHT to 2DGS2DGS · MipNeRF360PSNR: 27.48 -> 28.27Improved
add NHT to Triangle SplattingTriangle Splatting · MipNeRF360SSIM: 0.808 -> 0.807No clear effect
add NHT to Triangle SplattingTriangle Splatting · MipNeRF360PSNR: 27.00 -> 27.52Improved
add NHT to 3DGUT-MCMC3DGUT-MCMC · MipNeRF360LPIPS: 0.247 -> 0.232Improved
add NHT to 3DGUT-MCMC3DGUT-MCMC · MipNeRF360 (standardized)FPS: 201 -> 140Hurt
add NHT to 3DGUT-MCMC3DGUT-MCMC · MipNeRF360 training timeminutes: 7.1 -> 14.5Hurt
increase per-primitive features from 48 to 64 (ablation)3DGUT-MCMC + NHT · MipNeRF360PSNR: 28.65 -> 28.68Improved
increase per-primitive feature dimension from 4 to 64 (ablation)NHT semantic reconstruction · Tanks & Temples truck, RGB+LSEGPSNR: 23.81 -> 26.42Improved
train and evaluate on JPEG references instead of downscaled PNGs (ablation)NHT · MipNeRF360PSNR: -0.284Hurt
use NHT instead of explicit BBSplat texture at equal primitive countBBSplat · MipNeRF360 300K primitivesPSNR: 27.09 -> 27.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy