City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Paul, Sayan, Ghosh, Sourav, Katageri, Siddharth, Maity, Soumyadip, Sinha, Sanjana, Bhowmick, Brojeshwar
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914614615212032
author Paul, Sayan
Ghosh, Sourav
Katageri, Siddharth
Maity, Soumyadip
Sinha, Sanjana
Bhowmick, Brojeshwar
author_facet Paul, Sayan
Ghosh, Sourav
Katageri, Siddharth
Maity, Soumyadip
Sinha, Sanjana
Bhowmick, Brojeshwar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30310
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images
Paul, Sayan
Ghosh, Sourav
Katageri, Siddharth
Maity, Soumyadip
Sinha, Sanjana
Bhowmick, Brojeshwar
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
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.
title City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2605.30310