Papers › ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

3 Apr 2023ICCV 2023 1arXiv:2304.01116archive 2025-07-28

Mingyuan Zhang, Xinying Guo, Liang Pan, Zhongang Cai, Fangzhou Hong, Huirong Li, Lei Yang, Ziwei Liu

3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions. However, the performance on more diverse motions remains unsatisfactory. In this work, we propose ReMoDiffuse, a diffusion-model-based motion generation framework that integrates a retrieval mechanism to refine the denoising process. ReMoDiffuse enhances the generalizability and diversity of text-driven motion generation with three key designs: 1) Hybrid Retrieval finds appropriate references from the database in terms of both semantic and kinematic similarities. 2) Semantic-Modulated Transformer selectively absorbs retrieval knowledge, adapting to the difference between retrieved samples and the target motion sequence. 3) Condition Mixture better utilizes the retrieval database during inference, overcoming the scale sensitivity in classifier-free guidance. Extensive experiments demonstrate that ReMoDiffuse outperforms state-of-the-art methods by balancing both text-motion consistency and motion quality, especially for more diverse motion generation.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mingyuan-zhang/ReMoDiffuse officialmentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Denoising Diversity Motion Generation Motion Synthesis Retrieval model

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Motion Synthesis	HumanML3D	ReMoDiffuse	Diversity	9.018	#15 of 37	Archive leaderboard	report
Motion Synthesis	HumanML3D	ReMoDiffuse	FID	0.103	#15 of 37	Archive leaderboard	report
Motion Synthesis	HumanML3D	ReMoDiffuse	Multimodality	1.795	#15 of 37	Archive leaderboard	report
Motion Synthesis	HumanML3D	ReMoDiffuse	R Precision Top3	0.795	#15 of 37	Archive leaderboard	report
Motion Synthesis	KIT Motion-Language	ReMoDiffuse	Diversity	10.80	#3 of 31	Archive leaderboard	report
Motion Synthesis	KIT Motion-Language	ReMoDiffuse	FID	0.155	#3 of 31	Archive leaderboard	report
Motion Synthesis	KIT Motion-Language	ReMoDiffuse	Multimodality	1.239	#3 of 31	Archive leaderboard	report
Motion Synthesis	KIT Motion-Language	ReMoDiffuse	R Precision Top3	0.765	#3 of 31	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections