ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
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. Project page: https://mingyuan-zhang.github.io/projects/ReMoDiffuse.html
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“ReMoDiffuse [51] decomposes complex descriptions into anatomical text scripts by using ChatGPT.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [51]
In the citing paper
“ReMoDiffuse [51] retrieves relevant motion entities and generates motions using diffusion models, with the semantic-modulated attention and condition mixture guidance.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [51]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Hierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 1×
“DALL-E2 [19] attempts to bridge the text embedding and image embedding from the CLIP [18].”
BackgroundImproved Denoising Diffusion Probabilistic Models
Nichol, A., & Dhariwal, P. (2021) · arXiv · doi:10.48550/arxiv.2102.09672 · Cited by 1,550 · cited 1×
“Diffusion models [10, 14] is a new class of generative models that have achieved impressive progress on text-to-image generation tasks.”
BackgroundGLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357 · cited 1×
“GLIDE [13] designs classifier-free guidance and proves its superiority compared to the CLIP guidance used in previous works.”
ResultMotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2022) · arXiv · doi:10.48550/arxiv.2208.15001 · Cited by 437
Self-citationGenerating Human Motion from Textual Descriptions with Discrete Representations
Zhang, J., Zhang, Y., Cun, X., Zhang, Y., Zhao, H., Lu, H., Shen, X., & Ying, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01415 · Cited by 328 · cited 4×
“Table 1 and Table 2 show the comparison between our proposed ReMoDiffuse and four other existing works, including recent diffusion models-based algorithms [24, 27], one VAE-based generative model [7], and one GPT-style generative model [26].”
MethodInfluentialTevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., & Bermano, A. H. (2022) · arXiv · doi:10.48550/arxiv.2209.14916 · Cited by 290
Re-Imagen: Retrieval-Augmented Text-to-Image Generator
Chen, W., Hu, H., Saharia, C., & Cohen, W. W. (2022) · arXiv · doi:10.48550/arxiv.2209.14491 · Cited by 55
Research works printed but not linked: 14
- 10.1109/3DV.2019.00084 · DOI · Paper page
- 10.1109/3DV57658.2022.00053 · DOI
- 10.1109/ICCV48922.2021.00143 · DOI · Paper page
- 10.1109/CVPR52688.2022.00509 · DOI · Paper page
- 10.1007/978-3-031-19833-5_34 · DOI · Paper page
- 10.1145/3394171.3413635 · DOI · Paper page
- 10.1109/ICCV.2019.00554 · DOI · Paper page
- 10.1109/ICCV48922.2021.01080 · DOI · Paper page
- 10.1007/978-3-031-20047-2_28 · DOI · Paper page
- 10.1089/big.2016.0028 · DOI · Paper page
- 10.1109/CVPR52688.2022.00777 · DOI · Paper page
- 10.1109/WACV48630.2021.00357 · DOI · Paper page
- 10.1007/978-3-031-20047-2_21 · DOI · Paper page
- Vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 30
Cited by
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
“To fit in the input length limit, it reserves the contexts that are most relevant to the query.”
InfluentialSelf-citationHaresamudram, H., Tang, C. I., Suh, S., Lukowicz, P., & Plötz, T. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3729467 · Cited by 33
“The utility of generated data for HAR is validated on a newly collected dataset, and a combination of real and synthetic data substantially outperforms using real pressure data only.”
Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence
Chen, L.-H., Zhang, Y., Yin, Z., Dou, Z., Chen, X., Wang, J., Komura, T., & Zhang, L. (2025) · Proceedings of the SIGGRAPH Asia 2025 Conference Papers · doi:10.1145/3757377.3763811 · Cited by 3
Haresamudram, H., Tang, C. I., Suh, S., Lukowicz, P., & Ploetz, T. (2024) · arXiv · Cited by 31
“The utility of generated data for HAR is validated on a newly collected dataset, and a combination of real and synthetic data substantially outperforms using real pressure data only.”
Metadata
- Authors
- Zhang, M., Guo, X., Pan, L., Cai, Z., Hong, F., Li, H., Yang, L., & Liu, Z.
- Affiliations
- Nanyang Technological University,S-Lab,Singapore
- Sensetime,China
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 364-373
- Cited by
- 195
- References
- 10
- Funders
- Ministry of Education
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model. https://app.cochat.ai/papers/10.1109/iccv51070.2023.00040
- The paper
- Zhang, M., Guo, X., Pan, L., Cai, Z., Hong, F., Li, H., Yang, L., & Liu, Z. (2023). ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.00040
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.