Guided Motion Diffusion for Controllable Human Motion Synthesis
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions. However, integrating spatial constraints, such as pre-defined motion trajectories and obstacles, remains a challenge despite being essential for bridging the gap between isolated human motion and its surrounding environment. To address this issue, we propose Guided Motion Diffusion (GMD), a method that incorporates spatial constraints into the motion generation process. Specifically, we propose an effective feature projection scheme that manipulates motion representation to enhance the coherency between spatial information and local poses. Together with a new imputation formulation, the generated motion can reliably conform to spatial constraints such as global motion trajectories. Furthermore, given sparse spatial constraints (e.g. sparse keyframes), we introduce a new dense guidance approach to turn a sparse signal, which is susceptible to being ignored during the reverse steps, into denser signals to guide the generated motion to the given constraints. Our extensive experiments justify the development of GMD, which achieves a significant improvement over state-of-the-art methods in text-based motion generation while allowing control of the synthesized motions with spatial constraints.
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.
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
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148 · cited 1×
“Then, to address the highly sparse guidance, we draw inspiration from the credit assignment problem in Reinforcement Learning [50, 54], where sparse rewards can be distributed along a trajectory to allow for efficient learning [3].”
BackgroundImage Super-Resolution Via Iterative Refinement
Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3204461 · Cited by 1,829 · cited 1×
“They have been used for tasks such as image generation [12], image super-resolution [30, 46], speech synthesis [26,26,39], video generation [19,22], 3D shape generation [38,55], and reinforcement learning [23].”
MethodImage Super-Resolution via Iterative Refinement
Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2021) · arXiv · doi:10.48550/arxiv.2104.07636 · Cited by 1,829
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image
Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A., Tzionas, D., & Black, M. J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01123 · Cited by 1,781 · cited 1×
“Recently, many diffusion-based motion generation models have been proposed [11, 25, 32, 62, 64] and demonstrate better quality compared to alternative models such as GAN or VAE.”
Instructpix2pix: Learning to follow image editing instructions
Brooks, T., Holynski, A., & Efros, A. A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01764 · Cited by 1,466 · cited 1×
“The surge in interest in DPMs may be attributed to their impressive controllable generation capabilities, including text-conditioned generation [45, 47, 48] and image editing [4, 6, 10, 19, 35].”
BackgroundSRDiff: Single image super-resolution with diffusion probabilistic models
Li, H., Yang, Y., Chang, M., Chen, S., Feng, H., Xu, Z., Li, Q., & Chen, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.01.029 · Cited by 777
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
DiffWave: A Versatile Diffusion Model for Audio Synthesis
Kong, Z., Ping, W., Huang, J., Zhao, K., & Catanzaro, B. (2020) · arXiv · doi:10.48550/arxiv.2009.09761 · Cited by 569
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
Li, R., Yang, S., Ross, D. A., & Kanazawa, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01315 · Cited by 553 · cited 1×
“Various conditions have been explored such as partial poses [14, 18, 54], trajectories [25, 56, 63], images [9,46], music [29,30,32], text [1,15,16,26,40], objects [59], action labels [17,39], or unconditioned [37,60,64,66].”
Background
Cited by
AnyTop: Character Animation Diffusion with Any Topology
Gat, I., Raab, S., Tevet, G., Reshef, Y., Bermano, A. H., & Cohen-Or, D. (2025) · Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers · doi:10.1145/3721238.3730621 · Cited by 9
Controllable Single-Shot Animation Blending with Temporal Conditioning
Tselepi, E., Thermos, S., & Potamianos, G. (2025) · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00050 · Cited by 1
“The advent of deep generative models has expanded the possibilities of generating motion, particularly through text-to-motion paradigms that map natural language to dynamic character movements [9, 14, 27].”
Metadata
- Authors
- Karunratanakul, K., Preechakul, K., Suwajanakorn, S., & Tang, S.
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 2151-2162
- OpenAlex
- W4390874263
- Cited by
- 161
- References
- 13
- FWCI
- 72.37
- Type
- conference paper
- Language
- en
- Open access
- green
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: Guided Motion Diffusion for Controllable Human Motion Synthesis. https://app.cochat.ai/papers/10.1109/iccv51070.2023.00205
- The paper
- Karunratanakul, K., Preechakul, K., Suwajanakorn, S., & Tang, S. (2023). Guided Motion Diffusion for Controllable Human Motion Synthesis. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.00205
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.