GaussianZoom：几何与语义引导的渐进式放大生成 3D 高斯泼溅
GaussianZoom: Progressive Zoom-in Generative 3D Gaussian Splatting with Geometric and Semantic Guidance
把基于深度的特征 warp 与 VLM 驱动的细节合成结合进多视图一致超分模块，可在低分辨率多视图输入下生成高倍放大的 3DGS 场景；其可扩展连续 LOD 层级通过动态调制高斯可见性实现无混叠跨尺度渲染，对需要极端放大或跨尺度一致性的新视角合成工作可直接复用。
原文依据 a novel multi-view consistent super-resolution module with depth-based feature warping and VLM-driven detail synthesis
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 GaussianZoom，一个生成式放大 3D 重建系统，采用迭代渐进式框架，结合几何一致场景建模与多尺度语义推理，从而能够从低分辨率输入实现高保真的极端放大渲染。为此，我们设计了一个新颖的多视图一致超分辨率模块，包含基于深度的特征 warp 与 VLM 驱动的细节合成，在丰富超出观测分辨率的细粒度外观的同时确保准确的多视图对应关系。为支持大倍率范围内的放大，我们进一步引入一种新的可扩展连续细节层次（Level-of-Detail）层级结构，通过动态调制高斯可见性实现平滑、无混叠的跨尺度渲染。在 Mip-NeRF360 与 Tanks&Temples 上的实验表明，GaussianZoom 在极端放大下取得了更优的感知质量、多视图一致性与鲁棒性，为生成式放大 3D 场景重建建立了一个强有力的基线。
英文原文摘要 1018 字符
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.