HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Motion Synthesis On Humanml3D

Metrics

Diversity
FID
Multimodality
R Precision Top3

Results

Performance results of various models on this benchmark

Paper TitleRepository
Language2Pose7.67611.02-0.486TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Diffuion Motion23.69210.21-0.735Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model-
Text2Gesture6.4095.012-0.345TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
TM2T8.5891.5012.4240.729TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
T2M9.1751.0872.2190.736Generating Diverse and Natural 3D Human Motions From Text-
TM2D (t2m)9.5131.0214.139-TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration
MAA8.230.774-0.676Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation-
MotionDiffuse9.4100.6301.5530.782MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
MDM9.5590.5442.7990.611Human Motion Diffusion Model
MLD9.7240.4732.4130.772Executing your Commands via Motion Diffusion in Latent Space
MotionLCM (4-step)9.6070.3042.2590.798MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
Motion Mamba9.8710.2812.2940.792Motion Mamba: Efficient and Long Sequence Motion Generation
Fg-T2M9.2780.2431.6140.783Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model-
FineMoGen9.2630.1512.6960.784FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
T2M-GPT (τ ∈ U[0, 1])9.7220.1411.8310.775T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
T2M-GPT (τ = 0)9.8440.1403.2850.685T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
GraphMotion9.6920.1162.7660.785Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs-
T2M-GPT (τ = 0.5)9.7610.1161.8560.775T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
AttT2M9.7000.1122.4520.786 AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism
EMDM9.5510.1121.6410.786EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
0 of 37 row(s) selected.
Motion Synthesis On Humanml3D | SOTA | HyperAI