用渐进式生成实现低分辨率输入下的超精度3D缩放渲染。
GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
- 分步迭代重建，融合几何与语义信息提升细节。
- 在Mip-NeRF360和Tanks&Temples上实现极端缩放下的清晰渲染。
- 支持大范围缩放，动态调节高斯点可见性避免伪影。
我们提出GaussianZoom，一种生成式渐进缩放3D重建系统，采用迭代渐进框架，结合几何一致的场景建模与多尺度语义推理，实现从低分辨率输入到高保真极端缩放渲染。为此，我们设计了一种新颖的多视图一致性超分辨率模块，通过基于深度的特征对齐与视觉语言模型驱动的细节合成，在保证多视角对应准确的同时，丰富超出观测分辨率的细粒度外观。为支持大范围缩放，我们引入可扩展的连续细节层级结构，动态调控高斯点可见性，实现平滑无伪影的跨尺度渲染。在Mip-NeRF360和Tanks&Temples上的实验表明，GaussianZoom在感知质量、多视角一致性及极端放大下的鲁棒性方面均表现卓越，为生成式缩放3D场景重建建立了强有力基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。