Metraipolis › archive › dc_9ace2f793fbb
TSGL: Teacher-Student Graph Learning for 3DGS Compression — arXiv:2609.38635
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38635
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:46:48.308Z
- SHA-256 of the archived text
b2cd28039ba4473882ff00b4d3bb5ac560564f1e64aaba69a847d8091411e12e- Stable URL of this page
https://metraipolis.com/documento/dc_9ace2f793fbb
How to cite
TSGL: Teacher-Student Graph Learning for 3DGS Compression — arXiv:2609.38635 — arXiv (en), https://arxiv.org/abs/2609.38635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ace2f793fbb (Metraipolis archive dc_9ace2f793fbb, sha256 b2cd28039ba4473882ff00b4d3bb5ac560564f1e64aaba69a847d8091411e12e)
BibTeX
@misc{dc9ace2f793fbb,
title = {TSGL: Teacher-Student Graph Learning for 3DGS Compression — arXiv:2609.38635},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38635},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ace2f793fbb; sha256 b2cd28039ba4473882ff00b4d3bb5ac560564f1e64aaba69a847d8091411e12e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D Gaussian Splatting (3DGS) is a popular representation for novel view synthesis. However, 3DGS contains millions of Gaussian primitives, each with rich attributes, resulting in large file sizes. We propose a novel 3DGS compression method based on Teacher-Student Graph Learning (TSGL) that operates directly on a trained model, without 3DGS retraining or access to training images. Specifically, for each block of Gaussian primitives, using decoded positions and DC spherical harmonic (SH) coefficients as predictors, we learn a signal-dependent geometry graph G encoding the pairwise similarities between neighbouring Gaussians via a teacher-student model. Given G, we perform Graph Fourier Transform (GFT) on the remaining attributes, so that signal energies are predominantly projected into the low-frequency coefficients for compact representation. On three standard benchmarks, the method reaches 27x to 33x compression with less than 0.6 dB of PSNR loss, improving on recent post-training compression methods in both size and rendering quality. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV). Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.38635 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T14:19:00.895Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).