Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Jiawei, Lyu, Linye, Tian, Zhuotao, Zhuo, Cheng, Li, Yu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Toward Physically Consistent Driving Video World Models under Challenging Trajectories
di: Zhou, Jiawei, et al.
Pubblicazione: (2026)

CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
di: Lyu, Linye, et al.
Pubblicazione: (2024)

RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
di: Zhou, Jiawei, et al.
Pubblicazione: (2024)

Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectors
di: Zhou, Jiawei, et al.
Pubblicazione: (2024)

SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World
di: Kim, Jungho, et al.
Pubblicazione: (2026)

Video-ToC: Video Tree-of-Cue Reasoning
di: Tan, Qizhong, et al.
Pubblicazione: (2026)

Understanding Real-World Traffic Safety through RoadSafe365 Benchmark
di: Liu, Xinyu, et al.
Pubblicazione: (2026)

MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving
di: Wang, Haiguang, et al.
Pubblicazione: (2025)

Unified Language-driven Zero-shot Domain Adaptation
di: Yang, Senqiao, et al.
Pubblicazione: (2024)

ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable
di: Yin, Yuan, et al.
Pubblicazione: (2024)

SafeAug: Safety-Critical Driving Data Augmentation from Naturalistic Datasets
di: Mo, Zhaobin, et al.
Pubblicazione: (2025)

EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settings
di: Hu, Yingdong, et al.
Pubblicazione: (2024)

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding
di: Zeng, Tong, et al.
Pubblicazione: (2025)

A Sanity Check for Multi-In-Domain Face Forgery Detection in the Real World
di: Cheng, Jikang, et al.
Pubblicazione: (2025)

AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
di: Hou, Yunhao, et al.
Pubblicazione: (2025)

Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes
di: Zhang, Qi, et al.
Pubblicazione: (2026)

Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis
di: Trinci, Tomaso, et al.
Pubblicazione: (2026)

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video
di: Fan, Junkai, et al.
Pubblicazione: (2024)

Abductive Ego-View Accident Video Understanding for Safe Driving Perception
di: Fang, Jianwu, et al.
Pubblicazione: (2024)

Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation Framework
di: Xiang, Xinhao, et al.
Pubblicazione: (2025)

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
di: Hu, Xiaotao, et al.
Pubblicazione: (2024)

Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
di: Li, Gengluo, et al.
Pubblicazione: (2026)

A Study of Finetuning Video Transformers for Multi-view Geometry Tasks
di: Wu, Huimin, et al.
Pubblicazione: (2025)

DriveCtrl: Conditioned Sim-to-Real Driving Video Generation
di: Zhao, Haonan, et al.
Pubblicazione: (2026)

Safe2Drive: Evaluating Safe Driving Behaviors of E2E Autonomous Driving Models
di: Sahu, Nishad, et al.
Pubblicazione: (2026)

UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving
di: Chen, Rui, et al.
Pubblicazione: (2024)

DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
di: Xia, Tianze, et al.
Pubblicazione: (2025)

MultiWorld: Scalable Multi-Agent Multi-View Video World Models
di: Wu, Haoyu, et al.
Pubblicazione: (2026)

MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis
di: Zhi, Yihao, et al.
Pubblicazione: (2025)

CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop Evaluation
di: Jing, Bowen, et al.
Pubblicazione: (2026)

MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesis
di: Du, Xiaobiao, et al.
Pubblicazione: (2024)

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
di: Jin, Song, et al.
Pubblicazione: (2026)

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
di: Wu, Xiaoyang, et al.
Pubblicazione: (2023)

GenWorld: Towards Detecting AI-generated Real-world Simulation Videos
di: Chen, Weiliang, et al.
Pubblicazione: (2025)

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance
di: Fan, Junkai, et al.
Pubblicazione: (2024)

DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
di: Ai, Yuang, et al.
Pubblicazione: (2024)

MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer
di: Wu, Guile, et al.
Pubblicazione: (2025)

SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation
di: Ma, Yingzi, et al.
Pubblicazione: (2026)

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models
di: Sheng, Zihao, et al.
Pubblicazione: (2025)

Mitigating Object Hallucinations via Sentence-Level Early Intervention
di: Peng, Shangpin, et al.
Pubblicazione: (2025)