CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations
cs.CV
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: 13 pages, 4 figures;
Project page: https://metadriverse.github.io/metaurban
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Code World Model: Coding Agent as World Brain
- Map2World: Segment Map Conditioned Text to 3D World Generation
- CityCraft: A Real Crafter for 3D City Generation
- CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
- Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion
- Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image
- An Embodied Generalist Agent in 3D World
- MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts
- Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization
- SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors
- MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
- Pixal3D: Pixel-Aligned 3D Generation from Images
- Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset
- Imagine a City: CityGenAgent for Procedural 3D City Generation
- SpatialLM: Training Large Language Models for Structured Indoor Modeling
- Seeing through Satellite Images at Street Views
- Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
- UrbanWorld: An Urban World Model for 3D City Generation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models