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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zhening, Song, Rui, Huang, Yushi, Hu, Yingdong, Zhang, Xinjie, Shao, Jiawei, Lin, Zehong, Zhang, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911295205277696
author Liu, Zhening
Song, Rui
Huang, Yushi
Hu, Yingdong
Zhang, Xinjie
Shao, Jiawei
Lin, Zehong
Zhang, Jun
author_facet Liu, Zhening
Song, Rui
Huang, Yushi
Hu, Yingdong
Zhang, Xinjie
Shao, Jiawei
Lin, Zehong
Zhang, Jun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00877
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling
Liu, Zhening
Song, Rui
Huang, Yushi
Hu, Yingdong
Zhang, Xinjie
Shao, Jiawei
Lin, Zehong
Zhang, Jun
Computer Vision and Pattern Recognition
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.
title Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00877