Research map / 3D vision / 3D generation
WildCity: A Real-World Dataset for City-Scale Rendering and Beyond
Xiangyu Han, Mengyu Yang, Jiaqi Li, Bowen Chang, Ziyu Chen, Hexu Zhao, Rahul Agrawal, Anthony Rodriguez, Rajani Acharya, Fiona Hua, Marco Pavone, Chen Feng and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add sky model (ablation) | WildCity baseline · Atlanta (0.25km) | Depth L1 (m): 148.54 -> 13.26 | Improved |
| add sky model (ablation) | WildCity baseline · Atlanta (0.25km) | PSNR: 24.72 -> 25.42 | Improved |
| add sky model (ablation) | WildCity baseline · Arlington (0.1km) | PSNR: 28.69 -> 29.60 | Improved |
| add rig pose optimization (ablation) | WildCity baseline · Atlanta (0.25km) | PSNR: 25.51 -> 25.42 | Hurt |
| add rig pose optimization (ablation) | WildCity baseline · Atlanta (0.25km) | Depth L1 (m): 14.29 -> 13.26 | Improved |
| add ground regularization (ablation) | WildCity baseline · Atlanta (0.25km) | PSNR: 26.35 -> 25.42 | Hurt |
| add ground regularization (ablation) | WildCity baseline · Atlanta (0.25km) | Depth L1 (m): 13.11 -> 13.26 | Hurt |
| add ground regularization (ablation) | WildCity baseline · Arlington (0.1km) | PSNR: 30.14 -> 29.60 | Hurt |
| use urban-tailored baseline instead of CityGS on a long trajectory | Ours · Atlanta-5k (2.5km) | Depth L1 (m): 8.349 -> 6.622 | Improved |
| use urban-tailored baseline instead of H-3DGS on short trajectory | Ours · Ann Arbor-0.5k (0.25km) | Depth L1 (m): 18.450 -> 15.158 | Improved |
| replace SLAM initialization with VGGT-Long outputs in CityGS | CityGS · Atlanta-5k (2.5km) | PSNR: 21.27 -> 13.40 | Hurt |
| add Difix3D+ repair on extrapolated views (ablation) | Ours · extrapolated views | visual quality | Improved |
Closest papers by meaning
- UrbanFeel:A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective (ICLR 2026 · similarity 0.88)
- Dynamic 3D Gaussian Fields for Urban Areas (NeurIPS 2024 · similarity 0.87)
- Multi-Level Neural Scene Graphs for Dynamic Urban Environments (CVPR 2024 · similarity 0.86)
- Swift-Mapping: Online Neural Implicit Dense Mapping in Urban Scenes (AAAI 2024 · similarity 0.86)
- UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios (AAAI 2025 · similarity 0.86)
- CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
