Imagen de Portada

From Diffusion to Flow: Efficient Motion Generation in MotionGPT3

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ban, Jaymin, Jeon, JiHong, Jeong, SangYeop
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators
por: Zhang, Yaqi, et al.
Publicado: (2023)

MotionGPT3: Human Motion as a Second Modality
por: Zhu, Bingfan, et al.
Publicado: (2025)

MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
por: Wang, Yuan, et al.
Publicado: (2024)

Spectral Motion Alignment for Video Motion Transfer using Diffusion Models
por: Park, Geon Yeong, et al.
Publicado: (2024)

Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching
por: Miao, Fangran, et al.
Publicado: (2026)

Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
por: Jeon, Junhyuk, et al.
Publicado: (2026)

MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks
por: Wu, Yiming, et al.
Publicado: (2024)

Spatio-Temporal Branching for Motion Prediction using Motion Increments
por: Wang, Jiexin, et al.
Publicado: (2023)

CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion
por: Sun, Jiarui, et al.
Publicado: (2023)

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
por: Yu, Sihyun, et al.
Publicado: (2024)

MotionStream: Real-Time Video Generation with Interactive Motion Controls
por: Shin, Joonghyuk, et al.
Publicado: (2025)

CoMotion: Concurrent Multi-person 3D Motion
por: Newell, Alejandro, et al.
Publicado: (2025)

BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation
por: Hosseyni, S. Rohollah, et al.
Publicado: (2024)

Flexible Motion In-betweening with Diffusion Models
por: Cohan, Setareh, et al.
Publicado: (2024)

Potential Based Diffusion Motion Planning
por: Luo, Yunhao, et al.
Publicado: (2024)

MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching
por: Wu, Yen-Siang, et al.
Publicado: (2025)

Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening
por: Adewole, Michael, et al.
Publicado: (2024)

Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
por: Lee, Giwon, et al.
Publicado: (2025)

Motion Generation: A Survey of Generative Approaches and Benchmarks
por: Khani, Aliasghar, et al.
Publicado: (2025)

UniMoGen: Universal Motion Generation
por: Khani, Aliasghar, et al.
Publicado: (2025)

A Survey on Human Interaction Motion Generation
por: Sui, Kewei, et al.
Publicado: (2025)

Direct Motion Models for Assessing Generated Videos
por: Allen, Kelsey, et al.
Publicado: (2025)

Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
por: Choi, Soojin, et al.
Publicado: (2026)

Scaling Large Motion Models with Million-Level Human Motions
por: Wang, Ye, et al.
Publicado: (2024)

SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
por: Hong, Seokhyeon, et al.
Publicado: (2025)

Unsupervised 4D Cardiac Motion Tracking with Spatiotemporal Optical Flow Networks
por: Teng, Long, et al.
Publicado: (2024)

Continual Learning of Conjugated Visual Representations through Higher-order Motion Flows
por: Marullo, Simone, et al.
Publicado: (2024)

Video Motion Transfer with Diffusion Transformers
por: Pondaven, Alexander, et al.
Publicado: (2024)

Diffusion Model-based Activity Completion for AI Motion Capture from Videos
por: Huayu, Gao, et al.
Publicado: (2025)

MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
por: Zhu, Ruijie, et al.
Publicado: (2024)

StableMotion: Repurposing Diffusion-Based Image Priors for Motion Estimation
por: Wang, Ziyi, et al.
Publicado: (2025)

Fleximo: Towards Flexible Text-to-Human Motion Video Generation
por: Zhang, Yuhang, et al.
Publicado: (2024)

CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videos
por: Panambur, Tejas, et al.
Publicado: (2025)

VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation
por: Yin, Shaofeng, et al.
Publicado: (2025)

Inference-time Stochastic Refinement of GRU-Normalizing Flow for Real-time Video Motion Transfer
por: Haque, Tasmiah, et al.
Publicado: (2025)

Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models
por: Mandelli, Lorenzo, et al.
Publicado: (2024)

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
por: Lu, Shunlin, et al.
Publicado: (2024)

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers
por: Tas, Omer Sahin, et al.
Publicado: (2024)

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
por: Cho, Jungbin, et al.
Publicado: (2024)

E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization
por: Pham, Trung X., et al.
Publicado: (2025)