Research map / 3D vision / Gaussian splatting
EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis
Alexander Mai, Peter Hedman, George Kopanas, Dor Verbin, David Futschik, Qiangeng Xu, Falko Kuester, Jonathan T. Barron, Yinda Zhang
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 |
|---|---|---|---|
| render with exact ray-traced blending instead of splatting (ablation) | EVER · Ablation subset (bicycle, counter, berlin) | PSNR: 26.63 -> 27.17 | Improved |
| add color blending to per-ray sorting (ablation) | EVER · Ablation subset (bicycle, counter, berlin) | PSNR: 26.79 -> 27.17 | Improved |
| use EVER renderer instead of 3DGS with the same densification changes (ablation) | 3DGS + Our Changes · Ablation subset (bicycle, counter, berlin) | PSNR: 26.94 -> 27.17 | Improved |
| apply EVER densification changes to 3DGS (ablation) | 3DGS · Ablation subset (bicycle, counter, berlin) | PSNR: 27.02 -> 26.94 | No clear effect |
| add anisotropic regularizer (ablation) | EVER · Ablation subset (bicycle, counter, berlin) | PSNR: 27.25 -> 27.17 | Mixed |
| add anisotropic regularizer (ablation) | EVER · Ablation subset (bicycle, counter, berlin) | FPS: 27.3 -> 41.9 | Improved |
| add extra points via inverse contraction (ablation) | EVER · Ablation subset (bicycle, counter, berlin) | PSNR: 27.19 -> 27.17 | No clear effect |
| randomize pixel centers during training (ablation) | EVER · Ablation subset (bicycle, counter, berlin) | PSNR: 27.08 -> 27.17 | Improved |
| use EVER exact blending instead of 3DGS (ablation) | 3DGS · DeepBlending popping | FLIP7 popping error: 0.0122 -> 0.0000 | Improved |
| use EVER instead of 3DGS (ablation) | 3DGS · Mip-NeRF360 | LPIPS: .216 -> .194 | Improved |
| use EVER instead of 3DGS (ablation) | 3DGS · Zip-NeRF | PSNR: 25.84 -> 26.58 | Improved |
| use EVER instead of 3DGS (ablation) | 3DGS · Mip-NeRF360 | FPS: 224 -> 36 | 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 2 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
- Radiance Meshes for Volumetric Reconstruction (CVPR 2026 · similarity 0.88)
- LinPrim: Linear Primitives for Differentiable Volumetric Rendering (NeurIPS 2025 · similarity 0.85)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.85)
- Volumetrically Consistent 3D Gaussian Rasterization (CVPR 2025 · similarity 0.85)
- UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering (NeurIPS 2026 · similarity 0.85)
- 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering (ICLR 2025 · similarity 0.84)
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.
