GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Jiale, Hu, Jiarui, Yang, Zesong, Luan, Kaixuan, Bao, Hujun, Cui, Zhaopeng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911694035353600
author Shi, Jiale
Hu, Jiarui
Yang, Zesong
Luan, Kaixuan
Bao, Hujun
Cui, Zhaopeng
author_facet Shi, Jiale
Hu, Jiarui
Yang, Zesong
Luan, Kaixuan
Bao, Hujun
Cui, Zhaopeng
contents We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale semantic reasoning to enable high-fidelity extreme zoom-in rendering from low-resolution inputs. To achieve this, we develop a novel multi-view consistent super-resolution module with depth-based feature warping and VLM-driven detail synthesis, ensuring accurate multi-view correspondence while enriching fine-scale appearance beyond the observed resolution. To support zooming across large magnification ranges, we further introduce a new expandable continuous Level-of-Detail hierarchy that dynamically modulates Gaussian visibility for smooth, alias-free cross-scale rendering. Experiments on Mip-NeRF360 and Tanks\&Temples demonstrate that GaussianZoom achieves superior perceptual quality, multi-view consistency, and robustness under extreme magnification, establishing a strong baseline for generative zoom-in 3D scene reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18252
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
Shi, Jiale
Hu, Jiarui
Yang, Zesong
Luan, Kaixuan
Bao, Hujun
Cui, Zhaopeng
Computer Vision and Pattern Recognition
We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene modeling and multi-scale semantic reasoning to enable high-fidelity extreme zoom-in rendering from low-resolution inputs. To achieve this, we develop a novel multi-view consistent super-resolution module with depth-based feature warping and VLM-driven detail synthesis, ensuring accurate multi-view correspondence while enriching fine-scale appearance beyond the observed resolution. To support zooming across large magnification ranges, we further introduce a new expandable continuous Level-of-Detail hierarchy that dynamically modulates Gaussian visibility for smooth, alias-free cross-scale rendering. Experiments on Mip-NeRF360 and Tanks\&Temples demonstrate that GaussianZoom achieves superior perceptual quality, multi-view consistency, and robustness under extreme magnification, establishing a strong baseline for generative zoom-in 3D scene reconstruction.
title GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.18252