Pith. sign in

REVIEW 3 cited by

RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians

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 2406.11836 v2 pith:IGDT7M5Y submitted 2024-06-17 cs.CV cs.GR

Bingling Li , Shengyi Chen , Luchao Wang , Kaimin Liao , Sijie Yan , Yuanjun Xiong This is my paper
classification cs.CVcs.GR
keywords trainingexplorequalitygaussianincreasingmethodmodelnumbers
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we explore the possibility of training high-parameter 3D Gaussian splatting (3DGS) models on large-scale, high-resolution datasets. We design a general model parallel training method for 3DGS, named RetinaGS, which uses a proper rendering equation and can be applied to any scene and arbitrary distribution of Gaussian primitives. It enables us to explore the scaling behavior of 3DGS in terms of primitive numbers and training resolutions that were difficult to explore before and surpass previous state-of-the-art reconstruction quality. We observe a clear positive trend of increasing visual quality when increasing primitive numbers with our method. We also demonstrate the first attempt at training a 3DGS model with more than one billion primitives on the full MatrixCity dataset that attains a promising visual quality.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. TemporalGS: Training-Free Plug-and-Play Acceleration for 3D Gaussian Splatting Rendering via Temporal Priors

    cs.CV 2026-07 conditional novelty 6.5 of 10

    TemporalGS accelerates 3DGS rendering up to 1.48× without training by culling redundant Gaussians and selectively rendering only tiles that cannot be warped from temporal geometry and appearance buffers.

  2. FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    FlexGaussian is a training-free pipeline that prunes and quantizes 3D Gaussian Splatting scenes, achieving up to 96.4% compression with less than 1 dB PSNR drop.

  3. Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting

    cs.CV 2025-05 conditional novelty 6.0 of 10

    MixGS trains a holistic 3D Gaussian Splatting model with a view-aware decoder and a mixing operation, reporting state-of-the-art rendering quality on four large-scale scenes.

Pith tools