Research map / 3D vision / Gaussian splatting
Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields
Mihnea Jurca, Bert hauwermeiren, Adrian Munteanu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add HYDRA learned lobe decomposition (ablation) | Fourier Splatting · Tanks and Temples | PSNR: -0.22 dB when removed | Improved |
| add straight-through estimator for gradients beyond primitive boundary (ablation) | Fourier Splatting · Tanks and Temples | PSNR: -0.34 dB when removed | Improved |
| add randomized cloning offset (ablation) | Fourier Splatting · Tanks and Temples | PSNR: -0.05 dB when removed | Improved |
| truncate Fourier coefficients from K=6 to K=1 (ablation) | Fourier Splatting (V3C compressed) · compressed scene | PSNR: 22.40 -> 12.66 | Hurt |
| truncate Fourier coefficients from K=6 to K=1 (ablation) | Fourier Splatting (V3C compressed) · compressed scene | bytes per primitive: 74.89 -> 61.92 | Improved |
| use Fourier boundary primitive instead of Triangle Splatting | Fourier Splatting · Mip-NeRF 360 average | PSNR: +0.67 dB | Improved |
| use Fourier boundary primitive instead of 2DGS surfel | Fourier Splatting · Mip-NeRF 360 average | PSNR: +0.81 dB | Improved |
| use Fourier primitive instead of 3DGS | Fourier Splatting · Mip-NeRF 360 average | PSNR: 26.98 -> 27.65 | Improved |
| use Fourier primitive instead of Triangle Splatting | Fourier Splatting · Mip-NeRF 360 average | LPIPS: 0.191 -> 0.193 | No clear effect |
| use Fourier primitive instead of BBSplat | Fourier Splatting · Tanks and Temples | PSNR: 25.12 -> 24.15 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Zip-NeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · better on 0 of 1 shared result
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
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.89)
- pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024 · similarity 0.88)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.88)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.88)
- Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering (CVPR 2025 · similarity 0.88)
- DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds (CVPR 2025 · similarity 0.87)
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.
