SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World Domain

• URL: http://arxiv.org/abs/2505.17727v1
• Date: Fri, 23 May 2025 10:45:43 GMT
• Title: SafeMVDrive: Multi-view Safety-Critical Driving Video Synthesis in the Real World Domain
• Authors: Jiawei Zhou, Linye Lyu, Zhuotao Tian, Cheng Zhuo, Yu Li,
• Abstract summary: We introduce SafeMVDrive, a framework to generate safety-critical, multi-view driving videos grounded in real-world domains.<n>We first enhance scene understanding ability of the trajectory generator by incorporating visual context.<n>We introduce a two-stage, controllable trajectory generation mechanism that produces collision-evasion trajectories.
• Score: 25.44145750579996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety-critical scenarios are rare yet pivotal for evaluating and enhancing the robustness of autonomous driving systems. While existing methods generate safety-critical driving trajectories, simulations, or single-view videos, they fall short of meeting the demands of advanced end-to-end autonomous systems (E2E AD), which require real-world, multi-view video data. To bridge this gap, we introduce SafeMVDrive, the first framework designed to generate high-quality, safety-critical, multi-view driving videos grounded in real-world domains. SafeMVDrive strategically integrates a safety-critical trajectory generator with an advanced multi-view video generator. To tackle the challenges inherent in this integration, we first enhance scene understanding ability of the trajectory generator by incorporating visual context -- which is previously unavailable to such generator -- and leveraging a GRPO-finetuned vision-language model to achieve more realistic and context-aware trajectory generation. Second, recognizing that existing multi-view video generators struggle to render realistic collision events, we introduce a two-stage, controllable trajectory generation mechanism that produces collision-evasion trajectories, ensuring both video quality and safety-critical fidelity. Finally, we employ a diffusion-based multi-view video generator to synthesize high-quality safety-critical driving videos from the generated trajectories. Experiments conducted on an E2E AD planner demonstrate a significant increase in collision rate when tested with our generated data, validating the effectiveness of SafeMVDrive in stress-testing planning modules. Our code, examples, and datasets are publicly available at: https://zhoujiawei3.github.io/SafeMVDrive/.

Related papers

• LLM-based Realistic Safety-Critical Driving Video Generation [4.537331974356809]
  We propose a framework that automatically synthesizes driving scenarios within the CARLA simulator.<n>The framework has flexibility in scenario scripting, efficient code-based control of traffic participants, and enforcement of realistic physical dynamics.<n>Our approach enables controllable scenario generation and facilitates the creation of rare but critical edge cases.
  arXiv  Detail & Related papers  (2025-07-02T00:45:19Z)
• Challenger: Affordable Adversarial Driving Video Generation [36.949064774296076]
  Challenger is a framework that produces physically plausible yet photorealistic adversarial driving videos.<n>As tested on the nuScenes dataset, Challenger generates a diverse range of aggressive driving scenarios.
  arXiv  Detail & Related papers  (2025-05-21T17:59:55Z)
• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos.<n>These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• Towards Intelligent Transportation with Pedestrians and Vehicles In-the-Loop: A Surveillance Video-Assisted Federated Digital Twin Framework [62.47416496137193]
  We propose a surveillance video assisted federated digital twin (SV-FDT) framework to empower ITSs with pedestrians and vehicles in-the-loop.<n>The architecture consists of three layers: (i) the end layer, which collects traffic surveillance videos from multiple sources; (ii) the edge layer, responsible for semantic segmentation-based visual understanding, twin agent-based interaction modeling, and local digital twin system (LDTS) creation in local regions; and (iii) the cloud layer, which integrates LDTSs across different regions to construct a global DT model in realtime.
  arXiv  Detail & Related papers  (2025-03-06T07:36:06Z)
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models [63.71984266104757]
  Multimodal Large Language Models (MLLMs) can process both visual and textual data.<n>We propose SafeAuto, a novel framework that enhances MLLM-based autonomous driving systems by incorporating both unstructured and structured knowledge.
  arXiv  Detail & Related papers  (2025-02-28T21:53:47Z)
• Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention [61.3281618482513]
  We present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos.<n>CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the dimensions.<n>CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos.
  arXiv  Detail & Related papers  (2024-12-04T18:02:49Z)
• Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey [61.39993881402787]
  World models and video generation are pivotal technologies in the domain of autonomous driving. This paper investigates the relationship between these two technologies. By analyzing the interplay between video generation and world models, this survey identifies critical challenges and future research directions.
  arXiv  Detail & Related papers  (2024-11-05T08:58:35Z)
• DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation [10.296670127024045]
  DriveScape is an end-to-end framework for multi-view, 3D condition-guided video generation. Our Bi-Directional Modulated Transformer (BiMot) ensures precise alignment of 3D structural information. DriveScape excels in video generation performance, achieving state-of-the-art results on the nuScenes dataset with an FID score of 8.34 and an FVD score of 76.39.
  arXiv  Detail & Related papers  (2024-09-09T09:43:17Z)
• Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance [24.671417176179187]
  Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned/clear video pairs.<n>We propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy.<n>Our approach comprises two key components: reference matching and video dehazing.
  arXiv  Detail & Related papers  (2024-05-16T11:28:01Z)
• M2DA: Multi-Modal Fusion Transformer Incorporating Driver Attention for Autonomous Driving [11.36165122994834]
  We propose a Multi-Modal fusion transformer incorporating Driver Attention (M2DA) for autonomous driving. By incorporating driver attention, we empower the human-like scene understanding ability to autonomous vehicles to identify crucial areas precisely and ensure safety.
  arXiv  Detail & Related papers  (2024-03-19T08:54:52Z)
• Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving [56.381918362410175]
  Drive-WM is the first driving world model compatible with existing end-to-end planning models. Our model generates high-fidelity multiview videos in driving scenes.
  arXiv  Detail & Related papers  (2023-11-29T18:59:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.