Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
City-Mesh3R is introduced as a scalable framework for reconstructing watertight city-scale 3D meshes directly from unordered image collections, addressing the limitations of NeRF and Gaussian Splatting-based methods which often produce incomplete or noisy geometries unsuitable for simulation. The method employs a divide-and-conquer strategy involving topological image clustering for sparse map reconstruction, geometry-aware camera selection, and curvature-aware adaptive remeshing for dense surface reconstruction and refinement. Experiments on city-scale datasets demonstrate the framework's ability to generate high-fidelity, watertight meshes with regular geometry, capturing fine surface details and scaling effectively in a distributed setting.
Finally, a way to generate simulation-ready, watertight 3D city meshes from images at scale, without the geometry flaws of NeRF or the computational bottlenecks of existing methods.
City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and complexity of urban scenes. Existing city-scale 3D reconstruction methods based on NeRF, Gaussian Splatting etc. often fail to recover 3D meshes ready for simulation due to incomplete/missing geometry and irregular, noisy surfaces. Scaling existing small-scale 3D reconstruction methods to arbitrarily large urban scenes is highly infeasible due to their computational complexity. We present City-Mesh3R, a scalable framework for reconstructing watertight surface meshes directly from large unordered image collections. Unlike recent methods which use global sparse SfM point-cloud initialization followed by a distributed 3D dense reconstruction of large-scale scenes, our method follows an end-to-end images-to-mesh 3D reconstruction approach using a divide-and-conquer strategy. The sparse city map is reconstructed via topological image clustering, cluster-wise independent sparse SfM and map merging, without need for exhaustive image feature matching. Then this map is partitioned spatially to perform geometry-aware camera selection, followed by dense surface reconstruction and surface refinement using curvature-aware adaptive vertex density remeshing. These partition meshes are then stitched together to produce the global mesh of the city. The proposed end-to-end framework is evaluated on city-scale reconstruction datasets. As demonstrated by our qualitative and quantitative results, our proposed method yields high-fidelity watertight 3D meshes with regular geometry, capturing fine surface details, and is suitable for scaling to arbitrarily large scenes owing to the end-to-end processing in a distributed setting.