Urban Scene Reconstruction

Latest papers

14 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations
Oct 13, 2026Jiahui Sun, Ran Bi, Yifei Liu +8Aerial 3D Reconstruction 3D Scene Representation
Nanjing University · Shanghai Artificial Intelligence Laboratory · Beihang University +3
3D Gaussian Splatting for Fine-grained Urban Scene Reconstruction via Semantic-guided Density Control and Loss Design
Oct 12, 2026Yueling Liao, San Jiang, Xing Zhang +1Urban Scene Reconstruction 3D Gaussian Splatting
School of Computer Science, China University of Geosciences (Wuhan), Wuhan, 430074, China · School of Architecture and Urban Planning, Shenzhen University, Shenzhen, 518060, China · Guangdong Key Laboratory of Urban Informatics, Shenzhen University, Shenzhen, 518060, China +1
Agentic Building-Aware Satellite Gaussian Splatting for Auditable Urban DSM Reconstruction
Sep 22, 2026Wentao Sun, Zhengsen Xu, Yiping Chen +23D Reconstruction Urban Scene Reconstruction
University of Waterloo, Department of Systems Design Engineering, Waterloo, Canada · University of Calgary, Department of Geomatics Engineering, Calgary, Canada · Sun Yat-sen University, School of Geospatial Engineering and Science, Zhuhai, China
HiCo-GS: Hierarchical Context Aggregation and Geometric Consistency for Octree Gaussian Splatting
Aug 14, 2026Wei Zhang, Shengkai Yu, Shiqiang Gong +3Urban Scene Reconstruction 3D Gaussian Splatting
School of Computer Science Northwestern Polytechnical University Xi’an, China · vivo BlueImage Lab vivo Mobile Communication Co., Ltd. Hangzhou, China
WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence
Jul 7, 2026Xiangyu Han, Mengyu Yang, Jiaqi Li +9Autonomous Driving Datasets 3D Reconstruction
May Mobility, Ann Arbor, MI, USA · New York University, New York, NY, USA · Stanford University, Stanford, CA, USA +1
Shell-Supervised Gaussian Splatting for Urban Real-to-Sim Reconstruction
Jun 29, 2026Yuan Yang, Peijun Lu, Fangzhou Lu +53D Gaussian Splatting 3D Reconstruction
Hong Kong Center for Construction Robotics · Tsinghua University
BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering
Jun 15, 2026Yi-Ruei Liu, Jie-Ying Lee, Zheng-Hui Huang +2Inverse Rendering Physical Consistency in Video Generation
National Yang Ming Chiao Tung University · University of Illinois Urbana-Champaign · National Taiwan University
SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
Jun 2, 2026Qingpo Wuwu, Xiaobao Wei, Peng Chen +63DGS Compression 3D Gaussian Splatting
Peking University China · Chinese Academy of Sciences China · University of Illinois Urbana-Champaign United States +1
City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images
May 28, 2026Sayan Paul, Sourav Ghosh, Siddharth Katageri +33D Reconstruction Multi-View 3D Reconstruction
Visual Computing & Embodied AI Lab, TCS Research, India
Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction
May 21, 2026Henry Che, Jingkang Wang, Yun Chen +33D Gaussian Splatting Diffusion Model Guidance
1Waabi · University of Illinois Urbana-Champaign · University of Toronto
Feed-Forward Gaussian Splatting from Sparse Aerial Views
May 19, 2026Dongli Wu, Zhuoxiao Li, Tongyan Hua +43D Gaussian Splatting 3D Reconstruction
1The Hong Kong University of Science and Technology (Guangzhou) · 2Peking University · 3The Ohio State University
Stitch4D: Sparse Multi-Location 4D Urban Reconstruction via Spatio-Temporal Interpolation
Apr 9, 2026Hina Kogure, Kei Katsumata, Taiki Miyanishi +14D Reconstruction Sparse-View 4D Reconstruction
Keio University, Japan · The University of Tokyo, Japan
WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformation
Feb 25, 2026Wenhua Wu, Huai Guan, Zhe Liu +1Urban Scene Reconstruction 3D Reconstruction
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Oct 17, 2025Jie-Ying Lee, Yi-Ruei Liu, Shr-Ruei Tsai +63D Reconstruction 3D Scene Generation
National Yang Ming Chiao Tung University · UIUC · University of Zaragoza +1

Oct 13, 2026J/K move · Enter open · S save

CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations

Jiahui Sun, Ran Bi, Yifei Liu, Xiaolong Zhou+7

Nanjing University · Shanghai Artificial Intelligence Laboratory · Beihang University+3

Aerial 3D Reconstruction 3D Scene Representation Urban Scene Reconstruction 3D Scene Generation 3D Reconstruction Sparse-View 3D Reconstruction+1

Open paper AskPDF arXiv

Urban spatial intelligence calls for 3D cities that agents can measure, interpret, and modify across successive tasks. Maintaining such cities as persistent, code-based states requires lightweight acquisition and support for consistent state updates without repeated dense reconstruction. We therefore formulate a new setting for grounded urban world construction: generating large-scale, instance-level parameterized 3D cities from one low-altitude aerial RGB image per region and known camera parameters, while recovering metrically scaled buildings and explicit road geometry and connectivity. We introduce CityCode, an agent-operable representation that unifies metric geometry, urban topology, visual semantics, and 3D assets through persistent entity identities, with dependency-aware versioned execution for validated updates and historical restoration. We further develop Air2Code to construct this representation by combining visual structure extraction with adapted metric depth estimation. To address occlusion and incomplete coverage, recovered structure and observed appearance guide generative completion and subsequent structure-aware 3D generation for buildings and backgrounds. Experiments on CitySample-Aerial and UrbanScene3D demonstrate substantially more accurate metric structure recovery and superior visual fidelity to the target cities compared with the evaluated baselines. Across 50 task chains of 50 steps each, CityCode supports continued querying, editing, planning, and historical restoration over evolving city states. Together, CityCode and Air2Code turn sparse aerial observations into persistent, agent-operable urban worlds for long-horizon urban spatial intelligence.