Image de couverture de livre

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Guosheng, Wang, Xiaofeng, Zhu, Zheng, Chen, Xinze, Huang, Guan, Bao, Xiaoyi, Wang, Xingang
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
par: Zhao, Guosheng, et autres
Publié: (2024)

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
par: Zhou, Yang, et autres
Publié: (2026)

ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation
par: Zhao, Guosheng, et autres
Publié: (2025)

UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
par: Zhao, Guosheng, et autres
Publié: (2026)

WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
par: Wang, Xiaofeng, et autres
Publié: (2024)

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
par: Wang, Boyuan, et autres
Publié: (2025)

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
par: Ni, Chaojun, et autres
Publié: (2024)

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
par: Ni, Chaojun, et autres
Publié: (2025)

GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning
par: Bao, Xiaoyi, et autres
Publié: (2025)

EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation
par: Wang, Xiaofeng, et autres
Publié: (2024)

DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion
par: Wang, Weijie, et autres
Publié: (2025)

HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration
par: Wang, Boyuan, et autres
Publié: (2025)

EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling
par: Wang, Boyuan, et autres
Publié: (2025)

DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding
par: Bao, Xiaoyi, et autres
Publié: (2025)

ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
par: Wang, Boyuan, et autres
Publié: (2026)

InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation
par: Yang, Zhuoran, et autres
Publié: (2026)

CoReS: Orchestrating the Dance of Reasoning and Segmentation
par: Bao, Xiaoyi, et autres
Publié: (2024)

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
par: Ni, Chaojun, et autres
Publié: (2025)

DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
par: Xia, Tianze, et autres
Publié: (2025)

Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding
par: Ouyang, Runqi, et autres
Publié: (2025)

ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Mask
par: Yang, Zhuoran, et autres
Publié: (2026)

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
par: Hu, Xiaotao, et autres
Publié: (2024)

DriveCtrl: Conditioned Sim-to-Real Driving Video Generation
par: Zhao, Haonan, et autres
Publié: (2026)

Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models
par: Wang, Jiahao, et autres
Publié: (2025)

GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation
par: Yang, Zhenya, et autres
Publié: (2025)

DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
par: Shi, Chen, et autres
Publié: (2026)

Epona: Autoregressive Diffusion World Model for Autonomous Driving
par: Zhang, Kaiwen, et autres
Publié: (2025)

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
par: Zhou, Yang, et autres
Publié: (2026)

Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
par: Rowe, Luke, et autres
Publié: (2025)

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
par: Min, Chen, et autres
Publié: (2024)

Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving
par: Wen, Yuqing, et autres
Publié: (2024)

RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer
par: Liu, Liu, et autres
Publié: (2025)

DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
par: Wu, Wei, et autres
Publié: (2024)

STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation
par: Wang, Jiamin, et autres
Publié: (2025)

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model
par: Zheng, Yupeng, et autres
Publié: (2025)

DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
par: Liu, Xiaolu, et autres
Publié: (2026)

SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation
par: Wang, Ruoyu, et autres
Publié: (2026)

MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving
par: Wang, Haiguang, et autres
Publié: (2025)

Enhancing End-to-End Autonomous Driving with Latent World Model
par: Li, Yingyan, et autres
Publié: (2024)

GenDDS: Generating Diverse Driving Video Scenarios with Prompt-to-Video Generative Model
par: Fu, Yongjie, et autres
Publié: (2024)