Driving World Models Move the Camera, Not the Scene
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-15
Terminology
Sources
- What-If World: A Causal Benchmark for General World Models in Embodied Scenarios
- GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
- Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning
- PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
- DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction
- WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion
- HelloWorld: Towards Practical Applications of Generative Driving World Models
- Orbis 2: A Hierarchical World Model for Driving
- Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset
- Overcoming Statistical Bias in Action-Controllable World Models
- Stabilizing Camera-Controlled Novel View Synthesis at Inference Time
- Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control
- Is Energy Guidance All You Need? Training-Free Norm Injection for Driving World Models
- VehDyn: A Driving World Model Benchmark for Vehicle Dynamics
- Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
- Taming Camera-Controlled Video Generation with Verifiable Geometry Reward
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs