Motion Synthesis On Kit Motion Language

评估指标

Diversity

FID

Multimodality

R Precision Top3

评测结果

各个模型在此基准测试上的表现结果

					Paper Title	Repository
Text2Gesture	9.334	12.12	-	0.338	TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Language2Pose	9.073	6.545	-	0.483	TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
TEMOS	10.84	3.717	0.532	0.687	Executing your Commands via Motion Diffusion in Latent Space
TM2T	9.473	3.599	3.292	0.587	TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
T2M	10.72	3.022	2.052	0.681	Generating Diverse and Natural 3D Human Motions From Text	-
MotionDiffuse	11.10	1.954	0.730	0.739	MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
AttT2M	10.96	0.870	2.281	0.751	AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism
T2M-GPT (τ = 0)	11.198	0.737	2.309	0.716	T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
T2M-GPT (τ = 0.5)	10.862	0.717	1.912	0.737	T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Fg-T2M	10.93	0.571	1.019	0.745	Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model	-
T2M-GPT (τ ∈ U[0, 1])	10.921	0.514	1.570	0.745	T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
MDM	10.847	0.497	1.907	0.396	Human Motion Diffusion Model
DiverseMotion	10.873	0.468	2.062	0.760	DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion	-
ParCo	10.95	0.453	1.245	0.772	ParCo: Part-Coordinating Text-to-Motion Synthesis
MMM (predict length)	10.633	0.429	1.105	0.718	MMM: Generative Masked Motion Model
MLD	10.80	0.404	2.192	0.734	Executing your Commands via Motion Diffusion in Latent Space
GUESS	10.933	0.371	2.732	0.751	GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation
MMM (gt length)	10.910	0.316	1.232	0.744	MMM: Generative Masked Motion Model
GraphMotion	11.12	0.313	3.627	0.769	Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs	-
MotionPCM	10.827	0.294	1.254	0.787	MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model	-

0 of 30 row(s) selected.