CSS: Overcoming Pose and Scene Challenges in Crowd-Sourced 3D Gaussian Splatting
This enables more accurate and flexible applications in AR, VR, and large-scale 3D reconstruction for historically significant but inaccessible scenes.
The paper tackles the problem of reconstructing 3D scenes from crowd-sourced images without known camera poses, achieving high-quality novel view synthesis under real-world conditions.
We introduce Crowd-Sourced Splatting (CSS), a novel 3D Gaussian Splatting (3DGS) pipeline designed to overcome the challenges of pose-free scene reconstruction using crowd-sourced imagery. The dream of reconstructing historically significant but inaccessible scenes from collections of photographs has long captivated researchers. However, traditional 3D techniques struggle with missing camera poses, limited viewpoints, and inconsistent lighting. CSS addresses these challenges through robust geometric priors and advanced illumination modeling, enabling high-quality novel view synthesis under complex, real-world conditions. Our method demonstrates clear improvements over existing approaches, paving the way for more accurate and flexible applications in AR, VR, and large-scale 3D reconstruction.