Research map / 3D vision / 3D generation
StyleCity: Large-Scale 3D Urban Scenes Stylization
Yingshu Chen, Huajian Huang, Tuan-Anh Vu, Ka Chun Shum, Sai-Kit Yeung
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 |
|---|---|---|---|
| StyleCity (neural texture on mesh, image+text) instead of ARF, StyleMesh, InstructN2N | city-scale stylization · 5 city models x 7 styles | eSSIM: 0.503 -> 0.623 (vs best baseline InstructN2N) | Improved |
| StyleCity instead of baselines on style match in user study | city-scale stylization · user study | style match (0-5): 2.402 -> 4.572 (vs best baseline StyleMesh) | Improved |
| remove view augmentation (aug) or progressive optimization (prog) (ablation) | StyleCity · ablation scene with 4 styles | eSSIM and LPIPS | Hurt |
| add local semantics-aware style loss and CLIP loss (ablation) | StyleCity · ablation scene with 4 styles | style detail (lit windows) versus content similarity | Mixed |
| add scale-adaptive style optimization (ablation) | StyleCity · challenging scenes | qualitative robustness | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StyleMesh — StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions (CVPR 2022) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles (NeurIPS 2025 · similarity 0.88)
- PNeSM: Arbitrary 3D Scene Stylization via Prompt-Based Neural Style Mapping (AAAI 2024 · similarity 0.88)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (AAAI 2024 · similarity 0.87)
- Multi-StyleGS: Stylized Gaussian Splatting with Multiple Styles (AAAI 2025 · similarity 0.87)
- ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
- S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes (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.
