Research map / 3D vision / 3D generation
SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving
Zhenpei Yang, Yuning Chai, Dragomir Anguelov, Yin Zhou, Pei Sun, Dumitru Erhan, Sean Rafferty, Henrik Kretzschmar
Check 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 |
|---|---|---|---|
| Replace direct surfel renderings with SurfelGAN-SAC images | Vehicle detector evaluated on WOD-EVAL · WOD-EVAL | AP@50: 0.521 -> 0.620 | Improved |
| Add adversarial loss to paired supervised training (ablation) | SurfelGAN-S · WOD-EVAL | AP@50: 0.576 -> 0.610 | Improved |
| Add unpaired data and cycle consistency to supervised adversarial training (ablation) | SurfelGAN-SA · WOD-EVAL | AP@50: 0.610 -> 0.620 | Improved |
| Add unpaired data and cycle consistency to supervised adversarial training (ablation) | SurfelGAN-SA · DCP | L1-distance: 0.240 -> 0.238 | Hurt |
| Add adversarial loss to paired supervised training (ablation) | SurfelGAN-S · DCP | L1-distance: 0.229 -> 0.240 | Hurt |
| Add WOD-TRAIN-NV surfel renderings to detector training | Vehicle detector · WOD-EVAL | AP@50: 0.219 -> 0.228 | Improved |
| Add WOD-TRAIN-NV SurfelGAN images to detector training | Vehicle detector · WOD-EVAL | AP@50: 0.219 -> 0.254 | Improved |
| Increase novel-view pose perturbation | SurfelGAN-SAC · WOD-EVAL-NV, d <= 1.0 versus 2.0 < d | AP@50: 0.574 -> 0.488 | Hurt |
| Use surfel inputs with coverage ratio at or below 0.3 rather than coverage above 0.5 | SurfelGAN · WOD-EVAL-NV | AP@50: 0.566 -> 0.490 | Hurt |
| Use SurfelGAN-S instead of direct surfel renderings (ablation) | Image synthesis evaluated on DCP · DCP | L1-distance: 0.262 -> 0.229 | Improved |
| Add cycle consistency and unpaired training data (ablation) | SurfelGAN-SA · WOD-EVAL-NV | AP@50: 0.567 -> 0.570 | Improved |
Closest papers by meaning
- LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World (CVPR 2020 · similarity 0.89)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · similarity 0.88)
- ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images (AAAI 2025 · similarity 0.87)
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.86)
- UniScene: Unified Occupancy-centric Driving Scene Generation (CVPR 2025 · similarity 0.86)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.85)
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.
