Pith. sign in

REVIEW 18 cited by

CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization

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 2311.18159 v3 pith:QHI6CPG3 submitted 2023-11-30 cs.CV

KL Navaneet , Kossar Pourahmadi Meibodi , Soroush Abbasi Koohpayegani , Hamed Pirsiavash This is my paper · ORCID
classification cs.CV
keywords gaussiangaussiansmethodrenderingparameterssimplestoragetime
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on K-means to quantize the Gaussian parameters while optimizing them. Then, we store the small codebook along with the index of the code for each Gaussian. We compress the indices further by sorting them and using a method similar to run-length encoding. Moreover, we use a simple regularizer to encourage zero opacity (invisible Gaussians) to reduce the storage and rendering time by a large factor through reducing the number of Gaussians. We do extensive experiments on standard benchmarks as well as an existing 3D dataset that is an order of magnitude larger than the standard benchmarks used in this field. We show that our simple yet effective method can reduce the storage cost for 3DGS by 40 to 50x and rendering time by 2 to 3x with a very small drop in the quality of rendered images.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 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. Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    SIG synchronizes training-image resolution and Gaussian densification to measured scene bandwidth, plus sphere constraints on primitives, delivering better PSNR and 1.4–1.5× per-block speedups on large outdoor scenes.

  3. CF3: Compact and Fast 3D Feature Fields

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CF3 builds a compact 3D feature field from a pre-trained 3DGS by feature lifting, per-Gaussian autoencoding, and adaptive sparsification, matching baseline segmentation quality with roughly 5% of the Gaussians.

  4. 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.

  5. 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.

  6. FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A single 3DGS model with a learned Gaussian selector and transform field renders at any requested compression ratio without fine-tuning.

  7. Adaptive Voxelization for Transform coding of 3D Gaussian splatting data

    eess.IV 2025-05 conditional novelty 6.0 of 10

    An adaptive voxelization scheme tailored to 3D Gaussian splatting, combined with attribute initialization for fine-tuning, enables hybrid transform coding that outperforms post-training codecs on two benchmark scenes.

  8. MGStream: Motion-aware 3D Gaussian for Streamable Dynamic Scene Reconstruction

    cs.CV 2025-05 conditional novelty 6.0 of 10

    MGStream identifies motion-related Gaussians from a motion mask and convex hull, deforms only those per frame, and optimizes color for emerging objects, improving streaming dynamic view synthesis.

  9. Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A dynamic scene rendering method that tags Gaussians as static or dynamic by their temporal scale, converting static ones to 3D to cut training time.

  10. GIFStream: 4D Gaussian-based Immersive Video with Feature Stream

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A 4D Gaussian representation with sparse time-dependent feature streams achieves state-of-the-art rate-distortion performance for immersive video, compressing dynamic scenes to a few megabytes while rendering in real time.

  11. 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A 3D Gaussian head avatar method uses triplanes for neutral appearance and per-blendshape 1D feature lines for dynamic opacity offsets, reaching 10MB storage and 300 FPS with competitive fidelity.

  12. BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation

    cs.CV 2025-01 conditional novelty 6.0 of 10

    BloomScene generates 3D scenes from text or images by combining progressive point cloud construction, depth-prior regularization, and hash-grid compression, cutting storage about 5.8x versus LucidDreamer.

  13. HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression

    cs.CV 2024-11 conditional novelty 6.0 of 10

    HEMGS compresses 3D Gaussian Splatting data with a single variable-rate model and a joint autoregressive/hyperprior entropy model, achieving roughly 40% smaller files than HAC at similar quality.

  14. Enhancing LLM Training via Spectral Clipping

    cs.LG 2026-03 unverdicted novelty 5.0 of 10

    SPECTRA improves LLM pretraining via post-clipping of update spectral norms and optional pre-clipping of gradient spikes, framed as Composite Frank-Wolfe regularization.

  15. Steepest Descent Density Control for Compact 3D Gaussian Splatting

    cs.CV 2025-05 conditional novelty 5.0 of 10

    SteepGS splits a 3D Gaussian only when a computed splitting matrix has a negative eigenvalue, placing two half-opacity offspring along the steepest descent direction, achieving about 50% point reduction with comparabl...

  16. 3D Gaussian Splatting Data Compression with Mixture of Priors

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A gated mixture of lightweight prior networks plus gradient-guided element-wise quantization cuts 3D Gaussian Splatting file sizes by about 10 to 40 percent at matched PSNR on the tested benchmarks.

  17. 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.

  18. SG-Splatting: Accelerating 3D Gaussian Splatting with Spherical Gaussians

    cs.CV 2024-12 conditional novelty 4.0 of 10

    Using three orthogonal spherical Gaussians plus low-degree spherical harmonics for color reduces 3D-GS storage by about 47% and speeds rendering by 1.4x to 1.5x with roughly unchanged PSNR.

Pith tools