Research map / Video / Action recognition
DriveGAN: Towards a Controllable High-Quality Neural Simulation
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 |
|---|---|---|---|
| Use a multi-patch multi-scale image discriminator instead of the plain StyleGAN discriminator (ablation) | DriveGAN image generation on Carla · Carla images | FID: 72.3 -> 67.1 | Helped |
| Optimize a DriveGAN sequence using differentiable simulation rather than use a randomly sampled sequence | DriveGAN · RWD, 25m look-ahead | BEV lane prediction distance (m): 0.91m -> 0.58m | Helped |
| Optimize a DriveGAN sequence using differentiable simulation rather than use a randomly sampled sequence | DriveGAN · RWD, 50m look-ahead | BEV lane prediction distance (m): 1.78m -> 1.00m | Helped |
| Optimize a DriveGAN sequence using differentiable simulation rather than use a randomly sampled sequence | DriveGAN · RWD, 75m look-ahead | BEV lane prediction distance (m): 2.95m -> 1.70m | Helped |
| Optimize a DriveGAN sequence using differentiable simulation rather than use a randomly sampled sequence | DriveGAN · RWD, 100m look-ahead | BEV lane prediction distance (m): 4.74m -> 2.99m | Helped |
Closest papers by meaning
- ReSim: Reliable World Simulation for Autonomous Driving (NeurIPS 2025 · similarity 0.86)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.85)
- DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model (NeurIPS 2024 · similarity 0.85)
- Glad: A Streaming Scene Generator for Autonomous Driving (ICLR 2025 · similarity 0.85)
- DualAD: Disentangling the Dynamic and Static World for End-to-End Driving (CVPR 2024 · similarity 0.85)
- VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation (NeurIPS 2024 · similarity 0.84)
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.