Pith. sign in

REVIEW 5 cited by

Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning

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 2406.18214 v2 pith:3NR2UDWZ submitted 2024-06-26 cs.CV

Muhammad Salman Ali , Maryam Qamar , Sung-Ho Bae , Enzo Tartaglione This is my paper
classification cs.CV
keywords modelsapproachbaselinecompressiongaussianmodelperformancepruning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

In recent times, the utilization of 3D models has gained traction, owing to the capacity for end-to-end training initially offered by Neural Radiance Fields and more recently by 3D Gaussian Splatting (3DGS) models. The latter holds a significant advantage by inherently easing rapid convergence during training and offering extensive editability. However, despite rapid advancements, the literature still lives in its infancy regarding the scalability of these models. In this study, we take some initial steps in addressing this gap, showing an approach that enables both the memory and computational scalability of such models. Specifically, we propose "Trimming the fat", a post-hoc gradient-informed iterative pruning technique to eliminate redundant information encoded in the model. Our experimental findings on widely acknowledged benchmarks attest to the effectiveness of our approach, revealing that up to 75% of the Gaussians can be removed while maintaining or even improving upon baseline performance. Our approach achieves around 50$\times$ compression while preserving performance similar to the baseline model, and is able to speed-up computation up to 600 FPS.

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. AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Texture-aware SuperCluster pruning plus an adaptive Gaussian head lets feed-forward 3DGS models hit a user budget β while outperforming post-hoc pruners on RE10K, ACID, DL3DV and DTU.

  2. NeRF Is a Valuable Assistant for 3D Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    NeRF-GS jointly optimizes a NeRF and a 3D Gaussian Splatting model in one scene, using shared features, residual corrections, and mutual loss constraints to beat both standalone methods.

  3. 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.

  4. SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping

    cs.GR 2025-06 conditional novelty 5.0 of 10

    Temporal sensitivity pruning plus grouped SE(3) motion distillation speeds up DeformableGS rendering by 6.78x to 13.71x and training by about 2.5x across 50 dynamic scenes in MonoDyGauBench.

  5. Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splatting

    cs.GR 2025-08 conditional novelty 4.0 of 10

    A three-stage perceive-sample-compress framework for 3D Gaussian Splatting improves rendering fidelity and storage efficiency across small and large scenes.

Pith tools