Copertina

DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhuo, Dong, Zheng, Wenzhao, Zuo, Sicheng, Yan, Siming, Hou, Lu, Zhou, Jie, Lu, Jiwen
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Vega: Learning to Drive with Natural Language Instructions
di: Zuo, Sicheng, et al.
Pubblicazione: (2026)

EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding
di: Wu, Yuqi, et al.
Pubblicazione: (2024)

Doe-1: Closed-Loop Autonomous Driving with Large World Model
di: Zheng, Wenzhao, et al.
Pubblicazione: (2024)

GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction
di: Zuo, Sicheng, et al.
Pubblicazione: (2024)

GPD-1: Generative Pre-training for Driving
di: Xie, Zixun, et al.
Pubblicazione: (2024)

QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction
di: Zuo, Sicheng, et al.
Pubblicazione: (2025)

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
di: Wu, Yuqi, et al.
Pubblicazione: (2025)

Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
di: Fei, Xin, et al.
Pubblicazione: (2024)

Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection
di: Zeng, Shuai, et al.
Pubblicazione: (2024)

OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View
di: Wang, Yanbo, et al.
Pubblicazione: (2025)

GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction
di: Huang, Yuanhui, et al.
Pubblicazione: (2024)

DVGT: Driving Visual Geometry Transformer
di: Zuo, Sicheng, et al.
Pubblicazione: (2025)

DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
di: Zuo, Sicheng, et al.
Pubblicazione: (2026)

Streaming 4D Visual Geometry Transformer
di: Zhuo, Dong, et al.
Pubblicazione: (2025)

Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image
di: Zhang, Yanran, et al.
Pubblicazione: (2025)

DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning
di: Liu, Zhe, et al.
Pubblicazione: (2025)

SFTok: Bridging the Performance Gap in Discrete Tokenizers
di: Rao, Qihang, et al.
Pubblicazione: (2025)

GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting
di: Dong, Jiajun, et al.
Pubblicazione: (2025)

Fast Shapley Value Estimation: A Unified Approach
di: Zhang, Borui, et al.
Pubblicazione: (2023)

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views
di: Fei, Xin, et al.
Pubblicazione: (2024)

OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving
di: Wang, Lening, et al.
Pubblicazione: (2024)

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
di: Lu, Hao, et al.
Pubblicazione: (2024)

Path Choice Matters for Clear Attribution in Path Methods
di: Zhang, Borui, et al.
Pubblicazione: (2024)

Preventing Local Pitfalls in Vector Quantization via Optimal Transport
di: Zhang, Borui, et al.
Pubblicazione: (2024)

GlobalMamba: Global Image Serialization for Vision Mamba
di: Wang, Chengkun, et al.
Pubblicazione: (2024)

Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention
di: Lu, Hannan, et al.
Pubblicazione: (2024)

4D Driving Scene Generation With Stereo Forcing
di: Lu, Hao, et al.
Pubblicazione: (2025)

Measuring 3D Spatial Geometric Consistency in Dynamic Generated Videos
di: Dou, Weijia, et al.
Pubblicazione: (2026)

4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
di: Tang, Xiao, et al.
Pubblicazione: (2025)

Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model
di: Wang, Lening, et al.
Pubblicazione: (2024)

UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving
di: Min, Chen, et al.
Pubblicazione: (2023)

DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
di: Liang, Yiyuan, et al.
Pubblicazione: (2024)

DriveSplat: Unified Neural Gaussian Reconstruction for Dynamic Driving Scenes
di: Wang, Cong, et al.
Pubblicazione: (2025)

DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion
di: Wang, Weijie, et al.
Pubblicazione: (2025)

Quantize-then-Rectify: Efficient VQ-VAE Training
di: Zhang, Borui, et al.
Pubblicazione: (2025)

V2M: Visual 2-Dimensional Mamba for Image Representation Learning
di: Wang, Chengkun, et al.
Pubblicazione: (2024)

Terra: Explorable Native 3D World Model with Point Latents
di: Huang, Yuanhui, et al.
Pubblicazione: (2025)

UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
di: Wang, Ziyi, et al.
Pubblicazione: (2025)

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
di: Zhou, Xin, et al.
Pubblicazione: (2026)

HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving
di: Wu, Zehuan, et al.
Pubblicazione: (2024)