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

TL;DR

GaussianZoom is a novel 3D reconstruction system enabling high-fidelity zoom-in rendering from low-resolution inputs through progressive, multi-scale, and geometry-consistent modeling techniques.

Contribution

It introduces a progressive zoom-in framework with a multi-scale semantic hierarchy and a super-resolution module for detailed 3D scene reconstruction.

Findings

Achieves superior perceptual quality and multi-view consistency.

Demonstrates robustness under extreme magnification.

Establishes a new baseline for generative zoom-in 3D reconstruction.

Abstract

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.