Neural Reparameterization for 3D Gaussian Splatting Compression

While effective in diverse applications, including 3D/4D novel-view synthesis, Gaussian Splatting typically requires substantial storage to represent high-quality scenes. Many existing compression methods partially formulate this problem as point-based coding, treating Gaussians as a set of primitives with positions (or anchor locations) and rich appearance and shape attributes. These positions must therefore be encoded at high precision, as the storage cost scales with the number of primitives. However, many different sets of Gaussians can render the same scene equally well, so it is their spatial distribution that carries visual information and needs to be transmitted rather than any particular set. In this work, we propose GSRC, a Gaussian Splatting compression framework that achieves efficient representation and compression through neural reparameterization, which represents the Gaussians implicitly as the output of two networks instead of storing them. The first network maps a set of deterministic pseudo-random samples to a coarse point cloud representing the scene geometry, while the second one predicts the fine attributes of the Gaussians at these points using multi-resolution hash tables. To enable compact storage, we apply rate-aware training and entropy-code the resulting network parameters. Our results demonstrate that point cloud compression is not strictly necessary to achieve high-quality Gaussian Splatting representations, and that GSRC yields strong compression performance while preserving rendering quality, through implicit representation learning and model compression alone. Before entropy coding, the reparameterized model is 4$\times$ smaller than 3D-GS on Mip-NeRF 360 at 0.5 dB higher PSNR, which we attribute to the prior of the network. After coding, GSRC is about 100$\times$ smaller than 3D-GS at 0.25 dB higher PSNR, outperforms recent codecs with context models in most cases, especially in SSIM and LPIPS, and requires 49% fewer bytes than HAC++ at equal PSNR while decoding 24$\times$ faster. The implementation will be released.