Motion Synthesis On Humanml3D

評価指標

Diversity

FID

Multimodality

R Precision Top3

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Diversity	FID	Multimodality	R Precision Top3	Paper Title	Repository
MDM	9.559	0.544	2.799	0.611	Human Motion Diffusion Model
FineMoGen	9.263	0.151	2.696	0.784	FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
MotionLCM (4-step)	9.607	0.304	2.259	0.798	MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
GraphMotion	9.692	0.116	2.766	0.785	Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
MotionDiffuse	9.410	0.630	1.553	0.782	MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
AttT2M	9.700	0.112	2.452	0.786	AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism
T2M-GPT (τ = 0)	9.844	0.140	3.285	0.685	T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
MLD	9.724	0.473	2.413	0.772	Executing your Commands via Motion Diffusion in Latent Space
ReMoDiffuse	9.018	0.103	1.795	0.795	ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model
GUESS	9.826	0.109	2.430	0.787	GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation
ParCo	9.576	0.109	1.382	0.801	ParCo: Part-Coordinating Text-to-Motion Synthesis
MotionPCM	9.575	0.030	1.714	0.842	MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model	-
TM2T	8.589	1.501	2.424	0.729	TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Fg-T2M	9.278	0.243	1.614	0.783	Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model	-
MCM	9.585	0.053	0.8104	0.788	MCM: Multi-condition Motion Synthesis Framework
EMDM	9.551	0.112	1.641	0.786	EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
T2M	9.175	1.087	2.219	0.736	Generating Diverse and Natural 3D Human Motions From Text
BAD (CBS)	9.688	0.049	1.119	0.800	BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation
BAMM	9.717	0.055	1.687	0.814	BAMM: Bidirectional Autoregressive Motion Model
MMM (gt length)	9.577	0.089	1.226	0.804	MMM: Generative Masked Motion Model

0 of 37 row(s) selected.