ProDiG：渐进式扩散引导高斯点云法用于空到地重建
ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction
AI总结：
本文提出ProDiG方法，通过扩散引导逐步将空视图转换为地面级视图，利用几何感知因果注意力模块和距离自适应高斯模块，实现高斯点云的渐进式优化，提升重建的几何一致性和鲁棒性。
摘要：
从仅有的空视图生成地面级视图和一致的3D站点模型具有挑战性，因为存在极端视角变化、缺失的中间观测和大规模变化。现有方法要么事后优化渲染结果，通常产生几何不一致的结果，要么依赖多海拔的地面真实数据，这很少可用。高斯点云法和基于扩散的优化改进了小变化下的保真度，但在空到地之间较大的差距时失效。为了解决这些限制，我们引入ProDiG（Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction），一种扩散引导框架，逐步将空3D表示转换为地面级保真度。ProDiG合成中间海拔视图，并在每个阶段使用几何感知因果注意力模块优化高斯表示，该模块将视图扩散注入极线结构。距离自适应高斯模块动态调整高斯尺度和不透明度，基于相机距离确保在大视角差距下的稳定重建。这些组件共同实现了无需额外地面真实视图的渐进式、几何基础的优化。在合成和现实数据集上的广泛实验表明，ProDiG生成视觉逼真且一致的地面级渲染和3D几何，显著优于现有方法在视觉质量、几何一致性和对极端视角变化的鲁棒性方面。项目页面：https://sirsh07.github.io/research/prodig
英文摘要：
Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings post-hoc, often producing geometrically inconsistent results, or rely on multi-altitude ground-truth, which is rarely available. Gaussian Splatting and diffusion-based refinements improve fidelity under small variations but fail under wide aerial-toground gaps. To address these limitations, we introduce ProDiG (Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction), a diffusionguided framework that progressively transforms aerial 3D representations toward ground-level fidelity. ProDiG synthesizes intermediate-altitude views and refines the Gaussian representation at each stage using a geometry-aware causal attention module that injects epipolar structure into reference-view diffusion. A distance-adaptive Gaussian module dynamically adjusts Gaussian scale and opacity based on camera distance, ensuring stable reconstruction across large viewpoint gaps. Together, these components enable progressive, geometrically grounded refinement without requiring additional ground-truth viewpoints. Extensive experiments on synthetic and real-world datasets demonstrate that ProDiG produces visually realistic ground-level renderings and coherent 3D geometry, significantly outperforming existing approaches in terms of visual quality, geometric consistency, and robustness to extreme viewpoint changes. Project Page: https://sirsh07.github.io/research/prodig
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
