Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling

2025-11-30

AI Summary

Existing compression methods for 3D Gaussian Splatting (3DGS) suffer from limited modeling capacity for long-range spatial dependencies, primarily due to narrow receptive fields in transform coding networks and insufficient context capacity in entropy models—challenges exacerbated by the large-scale nature of 3DGS data. Method: We propose the first feed-forward 3DGS compression framework. It constructs a large-scale spatial context structure via Morton-order indexing, designs a joint spatial-channel autoregressive entropy model, and introduces an attention-driven transform coding network to jointly overcome receptive-field and contextual modeling bottlenecks. Contribution/Results: Our method achieves up to 20× compression ratio under feed-forward inference, significantly outperforming existing generalizable 3DGS compression approaches and establishing new state-of-the-art performance.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

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 $20 imes$ compression ratio for 3DGS in a feed-forward inference and achieves state-of-the-art performance among generalizable codecs.

Problem

• Compress 3D Gaussian Splatting data efficiently
• Model long-range spatial dependencies in 3DGS compression
• Achieve high compression ratio with feed-forward inference

Innovation

• Large-scale context structure with Morton serialization
• Fine-grained space-channel auto-regressive entropy model
• Attention-based transform coding for wide neighbor feature aggregation