SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Haihong, Zou, Jianan, Zhou, Yuxin, He, Ying, Kang, Wenxiong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908704632209408
author Xiao, Haihong
Zou, Jianan
Zhou, Yuxin
He, Ying
Kang, Wenxiong
author_facet Xiao, Haihong
Zou, Jianan
Zhou, Yuxin
He, Ying
Kang, Wenxiong
contents We present SplatCo, a structure-view collaborative Gaussian splatting framework for high-fidelity rendering of complex outdoor scenes. SplatCo builds upon three novel components: 1) a cross-structure collaboration module that combines global tri-plane representations, which capture coarse scene layouts, with local context grid features representing fine details. This fusion is achieved through a hierarchical compensation mechanism, ensuring both global spatial awareness and local detail preservation; 2) a cross-view pruning mechanism that removes overfitted or inaccurate Gaussians based on structural consistency, thereby improving storage efficiency and preventing rendering artifacts; 3) a structure view co-learning module that aggregates structural gradients with view gradients,thereby steering the optimization of Gaussian geometric and appearance attributes more robustly. By combining these key components, SplatCo effectively achieves high-fidelity rendering for large-scale scenes. Code and project page are available at https://splatco-tech.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17951
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
Xiao, Haihong
Zou, Jianan
Zhou, Yuxin
He, Ying
Kang, Wenxiong
Computer Vision and Pattern Recognition
We present SplatCo, a structure-view collaborative Gaussian splatting framework for high-fidelity rendering of complex outdoor scenes. SplatCo builds upon three novel components: 1) a cross-structure collaboration module that combines global tri-plane representations, which capture coarse scene layouts, with local context grid features representing fine details. This fusion is achieved through a hierarchical compensation mechanism, ensuring both global spatial awareness and local detail preservation; 2) a cross-view pruning mechanism that removes overfitted or inaccurate Gaussians based on structural consistency, thereby improving storage efficiency and preventing rendering artifacts; 3) a structure view co-learning module that aggregates structural gradients with view gradients,thereby steering the optimization of Gaussian geometric and appearance attributes more robustly. By combining these key components, SplatCo effectively achieves high-fidelity rendering for large-scale scenes. Code and project page are available at https://splatco-tech.github.io.
title SplatCo: Structure-View Collaborative Gaussian Splatting for Detail-Preserving Rendering of Large-Scale Unbounded Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.17951