Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling
This addresses the data size barrier for 3DGS in applications like 3D graphics and VR, offering a practical, generalizable solution, though it is incremental as it builds on existing feed-forward compression methods.
The paper tackles the problem of compressing 3D Gaussian Splatting (3DGS) representations, which are large and hinder adoption, by proposing a feed-forward compression framework that models long-range spatial dependencies, achieving a 20× compression ratio and state-of-the-art performance among generalizable codecs.
3D Gaussian Splatting (3DGS) has emerged as a revolutionary 3D representation. However, its substantial data size poses a major barrier to widespread adoption. While feed-forward 3DGS compression offers a practical alternative to costly per-scene per-train compressors, existing methods struggle to model long-range spatial dependencies, due to the limited receptive field of transform coding networks and the inadequate context capacity in entropy models. In this work, we propose a novel feed-forward 3DGS compression framework that effectively models long-range correlations to enable highly compact and generalizable 3D representations. Central to our approach is a large-scale context structure that comprises thousands of Gaussians based on Morton serialization. We then design a fine-grained space-channel auto-regressive entropy model to fully leverage this expansive context. Furthermore, we develop an attention-based transform coding model to extract informative latent priors by aggregating features from a wide range of neighboring Gaussians. Our method yields a $20\times$ compression ratio for 3DGS in a feed-forward inference and achieves state-of-the-art performance among generalizable codecs.