Pith. sign in

REVIEW 5 cited by

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.01804 v6 pith:Z3RWHW2B submitted 2024-10-02 cs.CV

Alexander Mai , Peter Hedman , George Kopanas , Dor Verbin , David Futschik , Qiangeng Xu , Falko Kuester , Jonathan T. Barron
show 1 more author
Yinda Zhang
This is my paper
classification cs.CV
keywords renderingexactreal-timeachievesapproachellipsoidevergaussian
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering. Unlike recent rasterization based approach by 3D Gaussian Splatting (3DGS), our primitive based representation allows for exact volume rendering, rather than alpha compositing 3D Gaussian billboards. As such, unlike 3DGS our formulation does not suffer from popping artifacts and view dependent density, but still achieves frame rates of $\sim\!30$ FPS at 720p on an NVIDIA RTX4090. Since our approach is built upon ray tracing it enables effects such as defocus blur and camera distortion (e.g. such as from fisheye cameras), which are difficult to achieve by rasterization. We show that our method is more accurate with fewer blending issues than 3DGS and follow-up work on view-consistent rendering, especially on the challenging large-scale scenes from the Zip-NeRF dataset where it achieves sharpest results among real-time techniques.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Triangle Splatting for Real-Time Radiance Field Rendering

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A triangle-soup representation with a compact normalized window function is optimized end-to-end and beats Gaussian and convex splatting baselines on LPIPS while rendering at real-time rates.

  2. DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization

    cs.CV 2026-04 conditional novelty 5.5 of 10

    Native fisheye projection inside 3DGS plus feature-overlap cross-view joint optimization matches or beats prior fisheye and pinhole Gaussian methods on public datasets.

  3. A Bag of Tricks for Efficient Implicit Neural Point Clouds

    cs.GR 2025-08 conditional novelty 5.0 of 10

    A curated set of sampling, rasterization, and CNN pretraining tricks doubles rendering speed and cuts training time and memory of implicit neural point clouds with no loss of image quality.

  4. AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An anchor-graph structured 3D Gaussians representation, with graph-based feature propagation and region growing, achieves cleaner instance-level object selection and better editing/simulation results than free-Gaussia...

  5. Multi-Sample Anti-Aliasing and Constrained Optimization for 3D Gaussian Splatting

    cs.CV 2025-08 conditional novelty 3.0 of 10

    Combining 4x multisample anti-aliasing with adaptive error weighting and gradient-difference loss produces modest SSIM/LPIPS gains over vanilla 3DGS on Mip-NeRF360 and Tanks&Temples.

Pith tools