TSGL: Teacher-Student Graph Learning for 3DGS Compression

arXiv:2609.38635v1 Announce Type: cross Abstract: 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.

Related

• Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
• OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction
• GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow

Source: arXiv cs.CV | 2026-10-01