DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Weijie, Zhu, Jiagang, Zhang, Zeyu, Wang, Xiaofeng, Zhu, Zheng, Zhao, Guosheng, Ni, Chaojun, Wang, Haoxiao, Huang, Guan, Chen, Xinze, Zhou, Yukun, Qin, Wenkang, Shi, Duochao, Li, Haoyun, Xiao, Yicheng, Chen, Donny Y., Lu, Jiwen
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
by: Wang, Weijie, et al.
Published: (2025)

ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation
by: Zhao, Guosheng, et al.
Published: (2025)

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
by: Wang, Weijie, et al.
Published: (2025)

Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
by: Shi, Duochao, et al.
Published: (2025)

DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
by: Zhao, Guosheng, et al.
Published: (2024)

DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models
by: Zhang, Shenyu, et al.
Published: (2025)

ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction
by: Ni, Chaojun, et al.
Published: (2025)

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation
by: Zhao, Guosheng, et al.
Published: (2024)

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
by: Wang, Weijie, et al.
Published: (2026)

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
by: Ni, Chaojun, et al.
Published: (2025)

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration
by: Ni, Chaojun, et al.
Published: (2024)

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
by: Tan, Kaiyuan, et al.
Published: (2026)

FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis
by: Chen, Shijie, et al.
Published: (2025)

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
by: Zhu, Ziyue, et al.
Published: (2025)

DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes
by: Hou, Qirui, et al.
Published: (2025)

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
by: Wang, Weijie, et al.
Published: (2026)

ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction
by: Yu, Haibao, et al.
Published: (2026)

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
by: Zhou, Yang, et al.
Published: (2026)

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video
by: Gao, Zihui, et al.
Published: (2026)

WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration
by: Ni, Chaojun, et al.
Published: (2025)

WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens
by: Wang, Xiaofeng, et al.
Published: (2024)

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
by: Wang, Boyuan, et al.
Published: (2025)

GigaWorld-0: World Models as Data Engine to Empower Embodied AI
by: GigaWorld Team, et al.
Published: (2025)

RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer
by: Liu, Liu, et al.
Published: (2025)

SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
by: Herau, Quentin, et al.
Published: (2026)

SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
by: Zhu, Yicheng, et al.
Published: (2026)

UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
by: Zhao, Guosheng, et al.
Published: (2026)

SimGen: Simulator-conditioned Driving Scene Generation
by: Zhou, Yunsong, et al.
Published: (2024)

MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
by: Li, Haoyun, et al.
Published: (2025)

GigaBrain-0: A World Model-Powered Vision-Language-Action Model
by: GigaBrain Team, et al.
Published: (2025)

DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input
by: Tian, Qijian, et al.
Published: (2024)

EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer
by: Dong, Zhehao, et al.
Published: (2025)

VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction
by: Lin, Junhong, et al.
Published: (2025)

EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model
by: Dong, Ruixiao, et al.
Published: (2025)

XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method
by: Yu, Haochen, et al.
Published: (2025)

DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratch
by: Sun, Shuo, et al.
Published: (2023)

VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
by: Cho, Hoonhee, et al.
Published: (2025)

VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
by: Lang, Xiaolei, et al.
Published: (2026)

WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation
by: Lu, Jiachen, et al.
Published: (2023)

Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
by: Huang, Jiaxin, et al.
Published: (2026)