Imagen de Portada

GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Xiankang, Lin, Peile, Cui, Ying, Guo, Dongyan, Shen, Chunhua, Zhang, Xiaoqin
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

DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation
por: He, Xiankang, et al.
Publicado: (2024)

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
por: He, Xiankang, et al.
Publicado: (2025)

Geo-Align: Video Generation Alignment via Metric Geometry Reward
por: Li, Zizun, et al.
Publicado: (2026)

FineXtrol: Controllable Motion Generation via Fine-Grained Text
por: Shen, Keming, et al.
Publicado: (2025)

GeoDiffMM: Geometry-Guided Conditional Diffusion for Motion Magnification
por: Liu, Xuedeng, et al.
Publicado: (2025)

Decoupling Motion and Geometry in 4D Gaussian Splatting
por: Zhang, Yi, et al.
Publicado: (2026)

Advances in 4D Representation: Geometry, Motion, and Interaction
por: Zhao, Mingrui, et al.
Publicado: (2025)

Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance
por: Wang, Haoxuan, et al.
Publicado: (2025)

MARVIS: Motion & Geometry Aware Real and Virtual Image Segmentation
por: Wu, Jiayi, et al.
Publicado: (2024)

VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction
por: Hu, Yu, et al.
Publicado: (2025)

MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion
por: Tao, Peilin, et al.
Publicado: (2025)

LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation
por: Liu, Sheng, et al.
Publicado: (2025)

MotionScale: Reconstructing Appearance, Geometry, and Motion of Dynamic Scenes with Scalable 4D Gaussian Splatting
por: Zhou, Haoran, et al.
Publicado: (2026)

GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models
por: Ye, Zhankai, et al.
Publicado: (2026)

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis
por: Chen, Hongyuan, et al.
Publicado: (2026)

MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE
por: Zhu, Ruijie, et al.
Publicado: (2026)

MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation
por: Ding, Yanbo, et al.
Publicado: (2025)

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
por: Dai, Wenxun, et al.
Publicado: (2024)

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm
por: Guo, Ziyan, et al.
Publicado: (2025)

GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects
por: Shen, Licheng, et al.
Publicado: (2025)

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

Large Motion Model for Unified Multi-Modal Motion Generation
por: Zhang, Mingyuan, et al.
Publicado: (2024)

Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
por: Guo, Ruoxi, et al.
Publicado: (2024)

Event-Based Motion Segmentation by Motion Compensation
por: Stoffregen, Timo, et al.
Publicado: (2019)

Generative Human Motion Stylization in Latent Space
por: Guo, Chuan, et al.
Publicado: (2024)

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
por: Chu, Ruihang, et al.
Publicado: (2025)

Length-Aware Motion Synthesis via Latent Diffusion
por: Sampieri, Alessio, et al.
Publicado: (2024)

Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation
por: He, Jiayi, et al.
Publicado: (2025)

Channel-wise Motion Features for Efficient Motion Segmentation
por: Inoue, Riku, et al.
Publicado: (2025)

Segment Any Motion in Videos
por: Huang, Nan, et al.
Publicado: (2025)

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

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
por: Xiao, Lixing, et al.
Publicado: (2025)

Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors
por: Zhou, Pengfei, et al.
Publicado: (2026)

MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds
por: Dang, Ziqiang, et al.
Publicado: (2024)

Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
por: Xi, Lin, et al.
Publicado: (2023)

MOVE: Motion-Guided Few-Shot Video Object Segmentation
por: Ying, Kaining, et al.
Publicado: (2025)

POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
por: Zhang, Songyan, et al.
Publicado: (2025)

Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
por: Zhou, Haoran, et al.
Publicado: (2025)

Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation
por: Rong, Jintao, et al.
Publicado: (2025)

Towards Geometry-Aware and Motion-Guided Video Human Mesh Recovery
por: Chen, Hongjun, et al.
Publicado: (2026)