cs.CVOct 6, 2026

Efficient Gaussian Splatting Sequence Compression with Standard Video Codecs

Authors: Qi Yang, Shuting Xia, Le Yang, Geert Van Der Auwera, Zhu Li

Organizations: School of Science and Engineering, University of Missouri - Kansas City · Cooperative Medianet Innovation Center, Shanghai Jiaotong University · Electrical and Computer Engineering, University of Canterbury · Qualcomm

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

This paper presents a novel effective Gaussian Splatting (GS) sequence Compression method that utilizes the Video codec (GSCV). Existing video-based GS sequence compression relies on the Parallel Linear Assignment Sorting (PLAS) and tracked primitive information to convert GS into smooth 2D videos. However, tracked information is not available for most practical applications, and without it, using the vanilla PLAS can generate images exhibiting weak inter-frame correlation, due to its stochastic nature. GSCV incorporates a simple yet efficient Inter-PLAS method to produce close images between the I- and P-frames of GS, enhancing the inter-frame performance of video codec greatly. GSCV also realizes a new pipeline based on the state-of-the-art video codecs with high bit-depth GS images, achieving higher compressibility while simultaneously providing a higher quality upper bound. Experimental results show that the proposed GSCV exhibits obviously improved performance over MPEG video and point cloud-based anchors in GS sequence compression. The code is available at https://github.com/Qi-Yangsjtu/GSCV.

Figures & tables

Figure 1 . Examples of current inter-frame GS coding based on the video codecs.
Figure 2 . First row: PLAS results of “bartender” frames 1 and 2. Second row: frame 1/2 color DC and scale PLAS image.
Figure 3 . Framework of Inter-PLAS.
Figure 4 . PLAS loss and block size variation curve of “bartender” frame 1 (I-frame) and 2 (P-frame).
Figure 5 . Anchor-based PLAS refinement. First row: PLAS results for the 1st frame of “bartender”; second row: PLAS results for Pini′P_{ini}^{{}^{\prime}} ; third row: the proposed anchor-based PLAS refinement for Pini′P_{ini}^{{}^{\prime}} .
Figure 6 . Diagram of the proposed GSCV.
Figure 7 . Performance comparison on MPEG dataset. “T” and “ST” mean tracked and semi-tracked.
Figure 8 . Ablation study on (a)-(b): PLAS initialization and (c): effectiveness of Inter-PLAS.
Appendix figures & tables25 assets

Supplementary material from the paper’s appendix.

Appendix

 QP
RateCoordinateColor DCColor SH (degree 1/2/3)opacityscalerotation
R05lossless00/0/0000
R0477/12/17772
R031717/22/271772
R023722/27/3217127
R014732/37/42221217
Appendix
Table 1 . QP of five bitrates of GSCV
Figure 9 . PSNR performance comparison on MPEG tracked and semi-tracked dataset.
SequenceTracking modeProposed (HEVC)Proposed (VVC)
Ref. GSCodecRef. GPCCRef. GSCodecRef. GPCC
BartenderTracked−52.18%-52.18\%−14.81%-14.81\%−51.64%-51.64\%−13.59%-13.59\%
Semi-tracked−47.33%-47.33\%−10.18%-10.18\%−45.86%-45.86\%−6.70%-6.70\%
BreakfastTracked−50.01%-50.01\%−13.81%-13.81\%−50.29%-50.29\%−13.43%-13.43\%
Semi-tracked−46.98%-46.98\%−11.06%-11.06\%−45.29%-45.29\%−7.60%-7.60\%
CinemaTracked−51.64%-51.64\%−12.75%-12.75\%−51.81%-51.81\%−12.60%-12.60\%
Appendix
Table 2 . BD-Rate results of the proposed method under HEVC and VVC configurations. Negative values indicate bitrate savings relative to the corresponding reference method.
 Primitive Number
SequenceBartenderBreakfastCinema
Frame IndexTrackedSemi-trackedTrackedSemi-trackedTrackedSemi-tracked
1 570255 531263 426968
2 570104 530997 426752
3 569842 530998 426497
4 569733 530857 426209
Appendix
Table 3 . Number of primitives for MPEG tracked and semi-tracked sequences.
Figure 10 . Bitrate allocation of GSCV.
Figure 11 . Coding time of GSCV.
Figure 12 . Additional RD curves of GSCV on tracked “bartender”.
Figure 13 . Influence of data shuffle on GSCodec Studio on tracked dataset.
Figure 14 . Ablation study of anchor-based PLAS refinement.
Figure 15 . Influence of feature channels on Inter-PLAS
Figure 16 . RD curves of single-frame results.
Figure 20
Figure 19 . Illustration of residual map and statistic histogram.
Figure 20 . RD curves of different components.
ComponentQP
Color DC022273747
Color SHdegree107172232
degree2012222737
degree3017273242
Opacity017222732
Scaling07121722
Appendix
Table 4 . QP of different components
Figure 21 . RD curves of different components with smooth QP variation.
CodecGSCV-HM18.0GSCV-VTM23.11GSCV-libx265GSCV-libx264GSCodec StudioGPCC v1
Rate Pointencdecencdecencdecencdecencdecencdec
51183.53.911288.94.24.61.20.80.68.91.4304.186.0
41012.52.911234.23.34.10.90.70.68.51.4298.088.4
3540.32.16385.62.32.80.70.60.57.31.3291.786.7
2353.41.63482.81.72.30.60.50.56.41.3291.986.0
1301.51.32391.81.21.90.50.50.55.21.1293.285.4
Appendix
Table 5 . Encoding and decoding time of different codecs on one GoP (8 frames)
Figure 22 . RD curves of using FFMPEG codecs
Figure 23 . RD curves of A-3DGS methods.
Figure 24 . RD curves on “dance” and “basketball”.
Figure 25 . RD curves of using the Sandwich network.
Figure 26 . Snapshot of “dance” and “basketball”
Figure 27 . Snapshot of MPEG “bartender”.
Figure 28 . Snapshot of MPEG “breakfast”.
Figure 29 . Snapshot of MPEG “cinema”.

Explore similar work

CardsList

  1. GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion

    Jul 27, 2026Qiang Hu, Zhenlong Wu, Lei Huang +33DGS Compression3D Gaussian Splatting

    Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, 200240, China

  2. CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting

    May 25, 2026Pengpeng Yu, Runqing Jiang, Qi Zhang +33DGS Compression3D Gaussian Splatting

    Sun Yat-sen University, China · Pengcheng Laboratory, China · Peking University, China

  3. GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds

    Jun 4, 2026Rajrup Ghosh, Haodong Wang, Haoran Hong +63DGS Compression3D Gaussian Splatting

    University of Southern California