Imagen de Portada

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Jiahao, Xiong, Weitao, Deng, Jiacheng, Li, Peng, Huang, Tianyu, Dou, Zhiyang, Lin, Cheng, Yeung, Sai-Kit, Liu, Yuan
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
por: Lu, Jiahao, et al.
Publicado: (2026)

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
por: Lu, Jiahao, et al.
Publicado: (2024)

HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos
por: Xiong, Weitao, et al.
Publicado: (2025)

Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
por: Huang, Huajian, et al.
Publicado: (2023)

360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos
por: Xu, Yinzhe, et al.
Publicado: (2024)

360DVO: Deep Visual Odometry for Monocular 360-Degree Camera
por: Guo, Xiaopeng, et al.
Publicado: (2026)

Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
por: Lu, Jiahao, et al.
Publicado: (2025)

PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking
por: Li, Dong, et al.
Publicado: (2025)

3D Extended Object Tracking by Fusing Roadside Sparse Radar Point Clouds and Pixel Keypoints
por: Deng, Jiayin, et al.
Publicado: (2024)

VoxelTrack: Exploring Voxel Representation for 3D Point Cloud Object Tracking
por: Lu, Yuxuan, et al.
Publicado: (2024)

Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors
por: Dou, Zhiyang
Publicado: (2024)

SpatialTracker: Tracking Any 2D Pixels in 3D Space
por: Xiao, Yuxi, et al.
Publicado: (2024)

BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation
por: Lu, Jiahao, et al.
Publicado: (2024)

Beyond Pixel Histories: World Models with Persistent 3D State
por: Garcin, Samuel, et al.
Publicado: (2026)

Diff3DETR:Agent-based Diffusion Model for Semi-supervised 3D Object Detection
por: Deng, Jiacheng, et al.
Publicado: (2024)

AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations
por: Truong, Quang Trung, et al.
Publicado: (2025)

EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving
por: Lin, Jiacheng, et al.
Publicado: (2024)

Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation
por: Lu, Jiahao, et al.
Publicado: (2025)

FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Tracking
por: Zhou, Sifan, et al.
Publicado: (2026)

Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game
por: Kim, Jeonghwan, et al.
Publicado: (2025)

WcDT: World-centric Diffusion Transformer for Traffic Scene Generation
por: Yang, Chen, et al.
Publicado: (2024)

LocDreamer: World Model-Based Learning for Joint Indoor Tracking and Anchor Scheduling
por: Wang, Geng, et al.
Publicado: (2026)

St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
por: Feng, Haiwen, et al.
Publicado: (2025)

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
por: Zhang, Tingyang, et al.
Publicado: (2025)

Point Tracking Improves World Action Models
por: Guan, Jiarui, et al.
Publicado: (2026)

OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splatting
por: Li, Longwei, et al.
Publicado: (2024)

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
por: HunyuanWorld Team, et al.
Publicado: (2025)

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
por: Wang, Jiahao, et al.
Publicado: (2025)

CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
por: Zhao, Chengfeng, et al.
Publicado: (2026)

Open-World Drone Active Tracking with Goal-Centered Rewards
por: Sun, Haowei, et al.
Publicado: (2024)

Ego3DT: Tracking Every 3D Object in Ego-centric Videos
por: Hao, Shengyu, et al.
Publicado: (2024)

TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting
por: Tan, Yuyang, et al.
Publicado: (2026)

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
por: Yang, Yuxue, et al.
Publicado: (2026)

PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds
por: Xu, Weisheng, et al.
Publicado: (2024)

DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking
por: Hu, Guyue, et al.
Publicado: (2026)

Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
por: Jiang, Zeren, et al.
Publicado: (2026)

Unsupervised Template-assisted Point Cloud Shape Correspondence Network
por: Deng, Jiacheng, et al.
Publicado: (2024)

Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels
por: Mu, Chenyu, et al.
Publicado: (2025)

Pedestrian Tracking with Monocular Camera using Unconstrained 3D Motion Model
por: Krejčí, Jan, et al.
Publicado: (2024)

AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing
por: Liu, Tianyu, et al.
Publicado: (2026)