Research map / 3D vision / 3D generation
SceneGen: Learning To Generate Realistic Traffic Scenes
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Increase sample proposals from M=1 to M=10 (ablation) | SceneGen · ATG4D | Features MMD: 0.13 -> 0.11 | Helped |
| Increase sample proposals from M=1 to M=20 (ablation) | SceneGen · ATG4D | Features MMD: 0.13 -> 0.11 | Helped |
| Increase sample proposals from M=1 to M=10 (ablation) | SceneGen · ATG4D | Class MMD: 0.05 -> 0.20 | Hurt |
| Increase sample proposals from M=1 to M=20 (ablation) | SceneGen · ATG4D | Class MMD: 0.05 -> 0.30 | Hurt |
| Increase sample proposals from M=1 to M=10 (ablation) | SceneGen · ATG4D | Size MMD: 0.05 -> 0.06 | Hurt |
| Increase sample proposals from M=1 to M=20 (ablation) | SceneGen · ATG4D | Size MMD: 0.05 -> 0.07 | Hurt |
| Increase sample proposals from M=1 to M=10 (ablation) | SceneGen · ATG4D | Speed MMD: 0.10 -> 0.33 | Hurt |
| Increase sample proposals from M=1 to M=20 (ablation) | SceneGen · ATG4D | Speed MMD: 0.10 -> 0.41 | Hurt |
| Increase sample proposals from M=1 to M=10 (ablation) | SceneGen · ATG4D | Heading MMD: 0.10 -> 0.08 | Helped |
| Increase sample proposals from M=1 to M=20 (ablation) | SceneGen · ATG4D | Heading MMD: 0.10 -> 0.08 | Helped |
| Use SceneGen rather than Procedural | Vehicle scene generation · ATG4D | Size MMD: 0.15 -> 0.06 | Helped |
| Use SceneGen rather than Lane Graph | Vehicle scene generation · ATG4D | Speed MMD: 0.28 -> 0.19 | Helped |
Closest papers by meaning
- SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model (CVPR 2025 · similarity 0.90)
- Generating Multimodal Driving Scenes via Next-Scene Prediction (CVPR 2025 · similarity 0.88)
- SceneCrafter: Controllable Multi-View Driving Scene Editing (CVPR 2025 · similarity 0.88)
- Glad: A Streaming Scene Generator for Autonomous Driving (ICLR 2025 · similarity 0.88)
- SimGen: Simulator-conditioned Driving Scene Generation (NeurIPS 2024 · similarity 0.87)
- SEPT: Towards Efficient Scene Representation Learning for Motion Prediction (ICLR 2024 · similarity 0.87)
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.