Pith. sign in

REVIEW 5 cited by

Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs

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 2501.03399 v1 pith:NWI7YB6C submitted 2025-01-06 cs.CV cs.MM

Soonbin Lee , Fangwen Shu , Yago Sanchez , Thomas Schierl , Cornelius Hellge This is my paper
classification cs.CVcs.MM
keywords featureplanesrepresentationcodecsdatamethodstandardvideo
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

3D Gaussian Splatting is a recognized method for 3D scene representation, known for its high rendering quality and speed. However, its substantial data requirements present challenges for practical applications. In this paper, we introduce an efficient compression technique that significantly reduces storage overhead by using compact representation. We propose a unified architecture that combines point cloud data and feature planes through a progressive tri-plane structure. Our method utilizes 2D feature planes, enabling continuous spatial representation. To further optimize these representations, we incorporate entropy modeling in the frequency domain, specifically designed for standard video codecs. We also propose channel-wise bit allocation to achieve a better trade-off between bitrate consumption and feature plane representation. Consequently, our model effectively leverages spatial correlations within the feature planes to enhance rate-distortion performance using standard, non-differentiable video codecs. Experimental results demonstrate that our method outperforms existing methods in data compactness while maintaining high rendering quality. Our project page is available at https://fraunhoferhhi.github.io/CodecGS

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.

  1. OT-UVGS: Revisiting UV Mapping for Gaussian Splatting as a Capacity Allocation Problem

    cs.GR 2026-04 conditional novelty 7.0 of 10

    By treating UV mapping as a capacity allocation problem and using a lightweight optimal transport mapping, OT-UVGS improves rendering metrics and UV utilization in Gaussian Splatting.

  2. CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery

    eess.IV 2026-05 unverdicted novelty 6.0 of 10

    CATRF inserts standard codecs into the training loop of triplane radiance fields via straight-through estimation so the features adapt to codec distortions and achieve better rate-distortion performance for volumetric...

  3. CGHair: Compact Gaussian Hair Reconstruction with Card Clustering

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Hierarchical card clustering plus shared Gaussian texture codebooks reconstructs multi-view hair with 200x lower memory and 4x faster strand generation while matching prior 3DGS visual quality.

  4. POTR: Post-Training 3DGS Compression

    cs.CV 2026-01 unverdicted novelty 6.0 of 10

    POTR introduces simultaneous-effect pruning via a modified 3DGS rasterizer and entropy-reducing lighting coefficient recomputation to outperform prior post-training 3DGS compression methods in rate-distortion and infe...

  5. 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.

Pith tools