Saved in:
Bibliographic Details
Main Authors: Zhang, Shengjun, Fei, Xin, Liu, Fangfu, Song, Haixu, Duan, Yueqi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.16338
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913748170571776
author Zhang, Shengjun
Fei, Xin
Liu, Fangfu
Song, Haixu
Duan, Yueqi
author_facet Zhang, Shengjun
Fei, Xin
Liu, Fangfu
Song, Haixu
Duan, Yueqi
contents 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis performance. While conventional methods require per-scene optimization, more recently several feed-forward methods have been proposed to generate pixel-aligned Gaussian representations with a learnable network, which are generalizable to different scenes. However, these methods simply combine pixel-aligned Gaussians from multiple views as scene representations, thereby leading to artifacts and extra memory cost without fully capturing the relations of Gaussians from different images. In this paper, we propose Gaussian Graph Network (GGN) to generate efficient and generalizable Gaussian representations. Specifically, we construct Gaussian Graphs to model the relations of Gaussian groups from different views. To support message passing at Gaussian level, we reformulate the basic graph operations over Gaussian representations, enabling each Gaussian to benefit from its connected Gaussian groups with Gaussian feature fusion. Furthermore, we design a Gaussian pooling layer to aggregate various Gaussian groups for efficient representations. We conduct experiments on the large-scale RealEstate10K and ACID datasets to demonstrate the efficiency and generalization of our method. Compared to the state-of-the-art methods, our model uses fewer Gaussians and achieves better image quality with higher rendering speed.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16338
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Zhang, Shengjun
Fei, Xin
Liu, Fangfu
Song, Haixu
Duan, Yueqi
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis performance. While conventional methods require per-scene optimization, more recently several feed-forward methods have been proposed to generate pixel-aligned Gaussian representations with a learnable network, which are generalizable to different scenes. However, these methods simply combine pixel-aligned Gaussians from multiple views as scene representations, thereby leading to artifacts and extra memory cost without fully capturing the relations of Gaussians from different images. In this paper, we propose Gaussian Graph Network (GGN) to generate efficient and generalizable Gaussian representations. Specifically, we construct Gaussian Graphs to model the relations of Gaussian groups from different views. To support message passing at Gaussian level, we reformulate the basic graph operations over Gaussian representations, enabling each Gaussian to benefit from its connected Gaussian groups with Gaussian feature fusion. Furthermore, we design a Gaussian pooling layer to aggregate various Gaussian groups for efficient representations. We conduct experiments on the large-scale RealEstate10K and ACID datasets to demonstrate the efficiency and generalization of our method. Compared to the state-of-the-art methods, our model uses fewer Gaussians and achieves better image quality with higher rendering speed.
title Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16338