OmniNWM: Omniscient Driving Navigation World Models
Abstract
OmniNWM is a unified world model for autonomous driving that generates panoramic videos, encodes actions using Plucker ray-maps, and defines dense rewards based on 3D occupancy, achieving top performance in video generation, control, and stability.
Autonomous driving world models are expected to work effectively across three core dimensions: state, action, and reward. Existing models, however, are typically restricted to limited state modalities, short video sequences, imprecise action control, and a lack of reward awareness. In this paper, we introduce OmniNWM, an omniscient panoramic navigation world model that addresses all three dimensions within a unified framework. For state, OmniNWM jointly generates panoramic videos of RGB, semantics, metric depth, and 3D occupancy. A flexible forcing strategy enables high-quality long-horizon auto-regressive generation. For action, we introduce a normalized panoramic Plucker ray-map representation that encodes input trajectories into pixel-level signals, enabling highly precise and generalizable control over panoramic video generation. Regarding reward, we move beyond learning reward functions with external image-based models: instead, we leverage the generated 3D occupancy to directly define rule-based dense rewards for driving compliance and safety. Extensive experiments demonstrate that OmniNWM achieves state-of-the-art performance in video generation, control accuracy, and long-horizon stability, while providing a reliable closed-loop evaluation framework through occupancy-grounded rewards. Project page is available at https://github.com/Arlo0o/OmniNWM.
Community

OmniNWM addresses three core dimensions of autonomous driving world models:
📊 State: Joint generation of panoramic RGB, semantic, metric depth, and 3D occupancy videos
🎮 Action: Precise panoramic camera control via normalized Plücker ray-maps
🏆 Reward: Integrated occupancy-based dense rewards for driving compliance and safety
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- A Comprehensive Survey on World Models for Embodied AI (2025)
- OmniScene: Attention-Augmented Multimodal 4D Scene Understanding for Autonomous Driving (2025)
- RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation (2025)
- From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors (2025)
- OmniReason: A Temporal-Guided Vision-Language-Action Framework for Autonomous Driving (2025)
- VDRive: Leveraging Reinforced VLA and Diffusion Policy for End-to-end Autonomous Driving (2025)
- iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper