Imagen de Portada

V-DPM: 4D Video Reconstruction with Dynamic Point Maps

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sucar, Edgar, Insafutdinov, Eldar, Lai, Zihang, Vedaldi, Andrea
Formato:	Preprint
Publicado:	2026
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

Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
por: Sucar, Edgar, et al.
Publicado: (2025)

CoWTracker: Tracking by Warping instead of Correlation
por: Lai, Zihang, et al.
Publicado: (2026)

Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
por: Lai, Zihang, et al.
Publicado: (2025)

Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
por: Szymanowicz, Stanislaw, et al.
Publicado: (2024)

Syn4D: A Multiview Synthetic 4D Dataset
por: Jiang, Zeren, et al.
Publicado: (2026)

SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark
por: Kästingschäfer, Marius, et al.
Publicado: (2024)

DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction
por: Kaye, Ben, et al.
Publicado: (2024)

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

LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
por: Xu, Chenyi, et al.
Publicado: (2026)

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
por: Jiang, Zeren, et al.
Publicado: (2025)

Splatter Image: Ultra-Fast Single-View 3D Reconstruction
por: Szymanowicz, Stanislaw, et al.
Publicado: (2023)

Free3D: Consistent Novel View Synthesis without 3D Representation
por: Zheng, Chuanxia, et al.
Publicado: (2023)

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
por: Tschernezki, Vadim, et al.
Publicado: (2025)

DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
por: He, Zhuolin, et al.
Publicado: (2026)

LiDPM: Rethinking Point Diffusion for Lidar Scene Completion
por: Martyniuk, Tetiana, et al.
Publicado: (2025)

CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
por: Karaev, Nikita, et al.
Publicado: (2024)

Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images
por: Wu, Tianhao, et al.
Publicado: (2025)

NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
por: Chen, Weirong, et al.
Publicado: (2026)

CatFree3D: Category-agnostic 3D Object Detection with Diffusion
por: Bian, Wenjing, et al.
Publicado: (2024)

Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction
por: Chen, Weirong, et al.
Publicado: (2025)

DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
por: Tan, Lei, et al.
Publicado: (2026)

DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
por: Chen, Minghao, et al.
Publicado: (2024)

Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics
por: Li, Ruining, et al.
Publicado: (2024)

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
por: Li, Runjia, et al.
Publicado: (2025)

PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
por: Chen, Minghao, et al.
Publicado: (2024)

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
por: Engstler, Paul, et al.
Publicado: (2024)

Exploring Simple Open-Vocabulary Semantic Segmentation
por: Lai, Zihang
Publicado: (2024)

EPIC Fields: Marrying 3D Geometry and Video Understanding
por: Tschernezki, Vadim, et al.
Publicado: (2023)

Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion
por: Jakab, Tomas, et al.
Publicado: (2023)

LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models
por: Xie, Mingyang, et al.
Publicado: (2026)

SHIC: Shape-Image Correspondences with no Keypoint Supervision
por: Shtedritski, Aleksandar, et al.
Publicado: (2024)

Universal representations:The missing link between faces, text, planktons, and cat breeds
por: Bilen, Hakan, et al.
Publicado: (2017)

D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
por: Zeng, Qian, et al.
Publicado: (2025)

Lightplane: Highly-Scalable Components for Neural 3D Fields
por: Cao, Ang, et al.
Publicado: (2024)

SynCity: Training-Free Generation of 3D Worlds
por: Engstler, Paul, et al.
Publicado: (2025)

Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
por: Han, Junlin, et al.
Publicado: (2024)

Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
por: Wang, Yikai, et al.
Publicado: (2024)

Vista4D: Video Reshooting with 4D Point Clouds
por: Lin, Kuan Heng, et al.
Publicado: (2026)

Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting
por: Huang, Jiaxin, et al.
Publicado: (2025)

Dynamic 3D Point Cloud Sequences as 2D Videos
por: Zeng, Yiming, et al.
Publicado: (2024)