Low-Rank Approximation for Efficient Compression of Gaussian Splatting Spherical Harmonics
IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 9225-9238
DOI: 10.1109/tcsvt.2026.3670178 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Zhiwei Zhu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
3D Gaussian Splatting (3DGS) enables real-time, high-fidelity rendering but suffers from large model sizes, mainly due to the Spherical Harmonics (SH) coefficients used for view-dependent appearance modeling, whose parameter count scales quadratically ( $\mathcal {O}(L^{2})$ ) with the degree $L$ . This paper presents the first systematic study that reveals and leverages the intrinsic low-rank structure of SH coefficients in 3DGS. Unlike prior approaches that truncate spectral energy, the proposed low-rank paradigm compactly preserves spectral information, achieving high visual quality with substantially reduced storage. Two complementary approaches are introduced. (1) SHAC-PCA (Principal Component Analysis) is a plug-and-play post-hoc compressor that retains principal spectral variance for high-fidelity compression. (2) SHAC-LST (Learned Subset Transformation) is a training-integrated approach that decomposes Alternating Current (AC) of SH coefficients into low-dimensional subset coefficients and a shared transformation matrix, offering superior compression and even quality improvements through regularization. Both methods effectively reduce SH coefficients storage complexity to $\mathcal {O}(L)$ . Extensive experiments demonstrate that our approaches significantly reduce memory usage while maintaining or even improving rendering quality. The proposed techniques are highly versatile: SHAC-PCA can be applied to any pre-trained 3DGS model, while SHAC-LST supports end-to-end training or fine-tuning. Both methods are compatible with existing 3DGS compression pipelines, providing a practical and general solution for efficient compression of SH coefficients in 3DGS.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhu, Z., Li, S., Liao, Y., & Yu, L. (2026). Low-Rank Approximation for Efficient Compression of Gaussian Splatting Spherical Harmonics. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 9225-9238. https://doi.org/10.1109/tcsvt.2026.3670178
Vancouver
Zhu Z, Li S, Liao Y, Yu L. Low-Rank Approximation for Efficient Compression of Gaussian Splatting Spherical Harmonics. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):9225-9238. doi:10.1109/tcsvt.2026.3670178
BibTeX
@article{Zhu2026,
author = {Zhu, Zhiwei and Li, Sicheng and Liao, Yiyi and Yu, Lu},
title = {Low-Rank Approximation for Efficient Compression of Gaussian Splatting Spherical Harmonics},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {7},
pages = {9225--9238},
doi = {10.1109/tcsvt.2026.3670178}
}
EUVIMED