analiza aiqbench
AccidentSim addresses a critical gap in autonomous driving research by generating collision videos that are not only visually realistic but also physically consistent with real-world accident reports. The framework combines physical simulators, fine-tuned language models, and NeRF rendering to create synthetic datasets that accurately replicate post-collision trajectories, overcoming the limitations of existing methods that prioritize visuals over physics. This advancement provides a robust tool for training and validating safety-critical AI systems in scenarios where real data is scarce or dangerous to collect.
AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports
arXiv:2503.20654v5 Announce Type: replace-cross Abstract: Collecting real-world vehicle accident videos for autonomous driving research is challenging due to their rarity and complexity. While existing driving video generation methods may produce visually realistic videos, they often fail to deliver physically realistic simulations because they lack the capability to generate accurate post-collision trajectories. In this paper, we introduce AccidentSim, a novel framework that generates physically realistic vehicle collision videos by extracting and utilizing the physical clues and contextual information available in real-world vehicle accident reports. Specifically, AccidentSim leverages a reliable physical simulator to replicate post-collision vehicle trajectories from the physical and contextual information in the accident reports and to build a vehicle collision trajectory dataset. This dataset is then used to fine-tune a language model, enabling it to respond to user prompts and predict physically consistent post-collision trajectories across various driving scenarios based on user descriptions. Finally, we employ Neural Radiance Fields (NeRF) to render high-quality backgrounds, merging them with the foreground vehicles that exhibit physically realistic trajectories to generate vehicle collision videos. Experimental results demonstrate that the videos produced by AccidentSim excel in both visual and physical authenticity.
Abstract:Collecting real-world vehicle accident videos for autonomous driving research is challenging due to their rarity and complexity. While existing driving video generation methods may produce visually realistic videos, they often fail to deliver physically realistic simulations because they lack the capability to generate accurate post-collision trajectories. In this paper, we introduce AccidentSim, a novel framework that generates physically realistic vehicle collision videos by extracting and utilizing the physical clues and contextual information available in real-world vehicle accident reports. Specifically, AccidentSim leverages a reliable physical simulator to replicate post-collision vehicle trajectories from the physical and contextual information in the accident reports and to build a vehicle collision trajectory dataset. This dataset is then used to fine-tune a language model, enabling it to respond to user prompts and predict physically consistent post-collision trajectories across various driving scenarios based on user descriptions. Finally, we employ Neural Radiance Fields (NeRF) to render high-quality backgrounds, merging them with the foreground vehicles that exhibit physically realistic trajectories to generate vehicle collision videos. Experimental results demonstrate that the videos produced by AccidentSim excel in both visual and physical authenticity.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2503.20654 [cs.CV]
(or arXiv:2503.20654v5 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2503.20654 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 280 cuvinte
Subiecte conexe
With a feel for physics, AI models simulate a wider range of real-world scenarios
MIT News · 10 aug. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · 28 iul. 2026
VehDyn: A Driving World Model Benchmark for Vehicle Dynamics
arXiv · 29 sept. 2026