GSCodec Studio: A Modular Framework for Gaussian Splat Compression
Top Cited Papers
- 15 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 5483-5496
Abstract
3D Gaussian Splatting and its extension to 4D dynamic scenes enable photorealistic, real-time rendering from real-world captures, positioning Gaussian Splats (GS) as a promising format for next-generation immersive media. However, their high storage requirements pose significant challenges for practical use in sharing, transmission, and storage. Despite various studies exploring GS compression from different perspectives, these efforts remain scattered across separate repositories, complicating benchmarking and the integration of best practices. To address this gap, we present GSCodec Studio, a unified and modular framework for GS reconstruction, compression, and rendering. The framework incorporates a diverse set of 3D/4D GS reconstruction methods and GS compression techniques as modular components, facilitating flexible combinations and comprehensive comparisons. By integrating best practices from community research and our own explorations, GSCodec Studio supports the development of compact representation and compression solutions for static and dynamic Gaussian Splats. Specifically, we present Static and Dynamic GSCodec: Static GSCodec achieves competitive 3D Gaussian Splat rate-distortion performance with low decoding complexity, while Dynamic GSCodec delivers advanced 4D Gaussian Splat compression performance. The code for our framework is publicly available at https://github.com/JasonLSC/GSCodec_Studio, to advance the research on Gaussian Splats compression.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62571485)
- National Natural Science Foundation of China (U21B2004)
- National Natural Science Foundation of China (62441223)
- National Natural Science Foundation of China (62202418)
- Zhejiang University of Science and Technology
This publication has 50 references indexed in Scilit:
- SAGS: Structure-Aware 3D Gaussian Splatting2024
- Compact 3D Scene Representation via Self-Organizing Gaussian Grids2024
- CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization2024
- Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting2024
- GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation2024
- End-to-End Rate-Distortion Optimized 3D Gaussian Representation2024
- Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians2024
- MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-view Images2024
- MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation2024
- HAC: Hash-Grid Assisted Context for 3D Gaussian Splatting Compression2024