SRGS: Super-Resolution 3D Gaussian Splatting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Feng, Xiang, He, Yongbo, Chen, Linxi, Yang, Yan, Wang, Chengkai, Chen, Yifei, Zhong, Yixuan, Kuang, Zhenzhong, ding, Jiajun, Yin, Xufei, Zhu, Yanming
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911530610589696
author Feng, Xiang
He, Yongbo
Chen, Linxi
Yang, Yan
Wang, Chengkai
Chen, Yifei
Zhong, Yixuan
Kuang, Zhenzhong
ding, Jiajun
Yin, Xufei
Zhu, Yanming
author_facet Feng, Xiang
He, Yongbo
Chen, Linxi
Yang, Yan
Wang, Chengkai
Chen, Yifei
Zhong, Yixuan
Kuang, Zhenzhong
ding, Jiajun
Yin, Xufei
Zhu, Yanming
contents Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view geometric consistency. We revisit SRGS, a simple baseline that couples plug-in 2D SR priors with geometry-aware cross-view regularization, and observe that most subsequent advances follow the same paradigm, either strengthening prior injection, refining cross-view constraints, or modulating the objective. However, this shared structure is rarely formalized as a unified objective with explicit modules, limiting principled attribution of improvements and reusable design guidance. In this paper, we formalize SRGS as a unified modular framework that factorizes 3DGS SR into two components, prior injection and cross-view regularization, within a joint objective. This abstraction subsumes a broad family of recent methods as instantiations of the same recipe, enabling analysis beyond single-method innovation. Across five public benchmarks, we consolidate nine representative follow-up methods and trace reported improvements to specific modules and settings. Ablations disentangle the roles of priors and consistency, and stress tests under sparse-view input and challenging capture conditions characterize robustness. Overall, our study consolidates 3DGS SR into a coherent foundation and offers practical guidance for robust, comparable 3DGS SR methods.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10318
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SRGS: Super-Resolution 3D Gaussian Splatting
Feng, Xiang
He, Yongbo
Chen, Linxi
Yang, Yan
Wang, Chengkai
Chen, Yifei
Zhong, Yixuan
Kuang, Zhenzhong
ding, Jiajun
Yin, Xufei
Zhu, Yanming
Computer Vision and Pattern Recognition
Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view geometric consistency. We revisit SRGS, a simple baseline that couples plug-in 2D SR priors with geometry-aware cross-view regularization, and observe that most subsequent advances follow the same paradigm, either strengthening prior injection, refining cross-view constraints, or modulating the objective. However, this shared structure is rarely formalized as a unified objective with explicit modules, limiting principled attribution of improvements and reusable design guidance. In this paper, we formalize SRGS as a unified modular framework that factorizes 3DGS SR into two components, prior injection and cross-view regularization, within a joint objective. This abstraction subsumes a broad family of recent methods as instantiations of the same recipe, enabling analysis beyond single-method innovation. Across five public benchmarks, we consolidate nine representative follow-up methods and trace reported improvements to specific modules and settings. Ablations disentangle the roles of priors and consistency, and stress tests under sparse-view input and challenging capture conditions characterize robustness. Overall, our study consolidates 3DGS SR into a coherent foundation and offers practical guidance for robust, comparable 3DGS SR methods.
title SRGS: Super-Resolution 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.10318