Motion Synthesis on HumanML3D

Metric: Diversity (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Diversity▼	Extra Data	Paper	Date↕	Code
1	Diffuion Motion	23.692	No	Diffusion Motion: Generate Text-Guided 3D Human ...	2022-10-22	-
2	Motion Mamba	9.871	No	Motion Mamba: Efficient and Long Sequence Motion...	2024-03-12	Code
3	T2M-GPT (τ = 0)	9.844	No	T2M-GPT: Generating Human Motion from Textual De...	2023-01-15	Code
4	GUESS	9.826	No	GUESS:GradUally Enriching SyntheSis for Text-Dri...	2024-01-04	Code
5	T2M-GPT (τ = 0.5)	9.761	No	T2M-GPT: Generating Human Motion from Textual De...	2023-01-15	Code
6	MLD	9.724	No	Executing your Commands via Motion Diffusion in ...	2022-12-08	Code
7	T2M-GPT (τ ∈ U[0, 1])	9.722	No	T2M-GPT: Generating Human Motion from Textual De...	2023-01-15	Code
8	BAMM	9.717	No	BAMM: Bidirectional Autoregressive Motion Model	2024-03-28	Code
9	AttT2M	9.7	No	AttT2M: Text-Driven Human Motion Generation with...	2023-09-02	Code
10	BAD (OAAS)	9.694	No	BAD: Bidirectional Auto-regressive Diffusion for...	2024-09-17	Code
11	GraphMotion	9.692	No	-	-	Code
12	BAD (CBS)	9.688	No	BAD: Bidirectional Auto-regressive Diffusion for...	2024-09-17	Code
13	DiverseMotion (s=2)	9.683	Yes	DiverseMotion: Towards Diverse Human Motion Gene...	2023-09-04	-
14	MotionLCM (4-step)	9.607	No	MotionLCM: Real-time Controllable Motion Generat...	2024-04-30	Code
15	MCM	9.585	No	MCM: Multi-condition Motion Synthesis Framework	2024-04-19	Code
16	MMM (gt length)	9.577	No	MMM: Generative Masked Motion Model	2023-12-06	Code
17	ParCo	9.576	No	ParCo: Part-Coordinating Text-to-Motion Synthesis	2024-03-27	Code
18	MotionPCM	9.575	No	MotionPCM: Real-Time Motion Synthesis with Phase...	2025-01-31	-
19	MDM	9.559	No	Human Motion Diffusion Model	2022-09-29	Code
20	BiPO	9.556	No	BiPO: Bidirectional Partial Occlusion Network fo...	2024-11-28	-
21	DiverseMotion (s=1)	9.551	Yes	DiverseMotion: Towards Diverse Human Motion Gene...	2023-09-04	-
22	EMDM	9.551	No	EMDM: Efficient Motion Diffusion Model for Fast ...	2023-12-04	Code
23	Motion Anything	9.521	No	Motion Anything: Any to Motion Generation	2025-03-10	Code
24	TM2D (t2m)	9.513	No	TM2D: Bimodality Driven 3D Dance Generation via ...	2023-04-05	Code
25	Free-T2M (StableMoFusion)	9.48	No	Free-T2M: Frequency Enhanced Text-to-Motion Diff...	2025-01-30	Code
26	MMM (predict length)	9.411	No	MMM: Generative Masked Motion Model	2023-12-06	Code
27	MotionDiffuse	9.41	No	MotionDiffuse: Text-Driven Human Motion Generati...	2022-08-31	Code
28	Fg-T2M	9.278	No	Fg-T2M: Fine-Grained Text-Driven Human Motion Ge...	2023-09-12	-
29	FineMoGen	9.263	No	FineMoGen: Fine-Grained Spatio-Temporal Motion G...	2023-12-22	Code
30	T2M	9.175	No	-	-	Code
31	ReMoDiffuse	9.018	No	ReMoDiffuse: Retrieval-Augmented Motion Diffusio...	2023-04-03	Code
32	TM2T	8.589	No	TM2T: Stochastic and Tokenized Modeling for the ...	2022-07-04	Code
33	MAA	8.23	No	Make-An-Animation: Large-Scale Text-conditional ...	2023-05-16	-
34	Language2Pose	7.676	No	TM2T: Stochastic and Tokenized Modeling for the ...	2022-07-04	Code
35	Text2Gesture	6.409	No	TM2T: Stochastic and Tokenized Modeling for the ...	2022-07-04	Code

#1Diffuion MotionSOTA
23.692
Diversity· 2022-10-22
Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model
#2Motion Mamba
9.871
Diversity· 2024-03-12
Motion Mamba: Efficient and Long Sequence Motion Generation Code
#3T2M-GPT (τ = 0)
9.844
Diversity· 2023-01-15
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations Code
#4GUESS
9.826
Diversity· 2024-01-04
GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation Code
#5T2M-GPT (τ = 0.5)
9.761
Diversity· 2023-01-15
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations Code
#6MLD
9.724
Diversity· 2022-12-08
Executing your Commands via Motion Diffusion in Latent Space Code
#7T2M-GPT (τ ∈ U[0, 1])
9.722
Diversity· 2023-01-15
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations Code
#8BAMM
9.717
Diversity· 2024-03-28
BAMM: Bidirectional Autoregressive Motion Model Code
#9AttT2M
9.7
Diversity· 2023-09-02
AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism Code
#10BAD (OAAS)
9.694
Diversity· 2024-09-17
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation Code
#11GraphMotion
9.692
Diversity
No paperCode
#12BAD (CBS)
9.688
Diversity· 2024-09-17
BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation Code
#13DiverseMotion (s=2)
9.683
Diversity· Extra Data· 2023-09-04
DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion
#14MotionLCM (4-step)
9.607
Diversity· 2024-04-30
MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model Code
#15MCM
9.585
Diversity· 2024-04-19
MCM: Multi-condition Motion Synthesis Framework Code
#16MMM (gt length)
9.577
Diversity· 2023-12-06
MMM: Generative Masked Motion Model Code
#17ParCo
9.576
Diversity· 2024-03-27
ParCo: Part-Coordinating Text-to-Motion Synthesis Code
#18MotionPCM
9.575
Diversity· 2025-01-31
MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
#19MDMSOTA
9.559
Diversity· 2022-09-29
Human Motion Diffusion Model Code
#20BiPO
9.556
Diversity· 2024-11-28
BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis
#21DiverseMotion (s=1)
9.551
Diversity· Extra Data· 2023-09-04
DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion
#22EMDM
9.551
Diversity· 2023-12-04
EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation Code
#23Motion Anything
9.521
Diversity· 2025-03-10
Motion Anything: Any to Motion Generation Code
#24TM2D (t2m)
9.513
Diversity· 2023-04-05
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration Code
#25Free-T2M (StableMoFusion)
9.48
Diversity· 2025-01-30
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss Code
#26MMM (predict length)
9.411
Diversity· 2023-12-06
MMM: Generative Masked Motion Model Code
#27MotionDiffuseSOTA
9.41
Diversity· 2022-08-31
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model Code
#28Fg-T2M
9.278
Diversity· 2023-09-12
Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
#29FineMoGen
9.263
Diversity· 2023-12-22
FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing Code
#30T2M
9.175
Diversity
No paperCode
#31ReMoDiffuse
9.018
Diversity· 2023-04-03
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model Code
#32TM2TSOTA
8.589
Diversity· 2022-07-04
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts Code
#33MAA
8.23
Diversity· 2023-05-16
Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation
#34Language2Pose
7.676
Diversity· 2022-07-04
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts Code
#35Text2Gesture
6.409
Diversity· 2022-07-04
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts Code