Arbitrary-Scale 3D Gaussian Super-Resolution

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zeng, Huimin, Bai, Yue, Fu, Yun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909913062572032
author Zeng, Huimin
Bai, Yue
Fu, Yun
author_facet Zeng, Huimin
Bai, Yue
Fu, Yun
contents Existing 3D Gaussian Splatting (3DGS) super-resolution methods typically perform high-resolution (HR) rendering of fixed scale factors, making them impractical for resource-limited scenarios. Directly rendering arbitrary-scale HR views with vanilla 3DGS introduces aliasing artifacts due to the lack of scale-aware rendering ability, while adding a post-processing upsampler for 3DGS complicates the framework and reduces rendering efficiency. To tackle these issues, we build an integrated framework that incorporates scale-aware rendering, generative prior-guided optimization, and progressive super-resolving to enable 3D Gaussian super-resolution of arbitrary scale factors with a single 3D model. Notably, our approach supports both integer and non-integer scale rendering to provide more flexibility. Extensive experiments demonstrate the effectiveness of our model in rendering high-quality arbitrary-scale HR views (6.59 dB PSNR gain over 3DGS) with a single model. It preserves structural consistency with LR views and across different scales, while maintaining real-time rendering speed (85 FPS at 1080p).
format Preprint
id arxiv_https___arxiv_org_abs_2508_16467
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Arbitrary-Scale 3D Gaussian Super-Resolution
Zeng, Huimin
Bai, Yue
Fu, Yun
Computer Vision and Pattern Recognition
Existing 3D Gaussian Splatting (3DGS) super-resolution methods typically perform high-resolution (HR) rendering of fixed scale factors, making them impractical for resource-limited scenarios. Directly rendering arbitrary-scale HR views with vanilla 3DGS introduces aliasing artifacts due to the lack of scale-aware rendering ability, while adding a post-processing upsampler for 3DGS complicates the framework and reduces rendering efficiency. To tackle these issues, we build an integrated framework that incorporates scale-aware rendering, generative prior-guided optimization, and progressive super-resolving to enable 3D Gaussian super-resolution of arbitrary scale factors with a single 3D model. Notably, our approach supports both integer and non-integer scale rendering to provide more flexibility. Extensive experiments demonstrate the effectiveness of our model in rendering high-quality arbitrary-scale HR views (6.59 dB PSNR gain over 3DGS) with a single model. It preserves structural consistency with LR views and across different scales, while maintaining real-time rendering speed (85 FPS at 1080p).
title Arbitrary-Scale 3D Gaussian Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.16467