AI Paper Atlas

Research map / 3D vision / Gaussian splatting

RayGaussX: Accelerating Gaussian-Based Ray Marching for Real-Time and High-Quality Novel View Synthesis

Hugo Blanc, Jean-Emmanuel Deschaud, Alexis Paljic

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 3 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
add new distance-corrected densification criterion (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)PSNR: 28.14 -> 28.38Improved
add new densification criterion (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)FPS: 1.5 -> 1.8Improved
add empty space skipping and adaptive sampling (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)FPS: 1.5 -> 5.9Improved
add empty space skipping and adaptive sampling (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)PSNR: 28.14 -> 28.14No clear effect
add Z-order reindexing and ray coherence (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)FPS: 1.5 -> 3.6Improved
add isotropic scale loss (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)FPS: 1.5 -> 10.1Improved
add isotropic scale loss (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)PSNR: 28.14 -> 28.12Hurt
add isotropic scale loss (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)Train time: 297min -> 133minImproved
combine all four contributions (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)FPS: 1.5 -> 27.4Improved
combine all four contributions (ablation)optimized RayGauss · Mip-NeRF360 garden (ablation)Train time: 297min -> 84minImproved
replace RayGauss with RayGaussXRayGauss · Tanks&TemplesPSNR: 23.20 -> 23.76Improved
replace RayGauss with RayGaussXRayGauss · Mip-NeRF360 (9 scenes)FPS: 0.5 -> 24.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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