The DOI matches its Crossref record; the references it cites are not checked yet.
ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters
Open accessAbstract
Motion retargeting is a promising approach for generating natural and compelling animations for nonhuman characters. However, it is challenging to translate human movements into semantically equivalent motions for target characters with different morphologies due to the ambiguous nature of the problem. This work presents a novel learning-based motion retargeting framework, Adversarial Correspondence Embedding (ACE), to retarget human motions onto target characters with different body dimensions and structures. Our framework is designed to produce natural and feasible character motions by leveraging generative-adversarial networks (GANs) while preserving high-level motion semantics by introducing an additional feature loss. In addition, we pretrain a character motion prior that can be controlled in a latent embedding space and seek to establish a compact correspondence. We demonstrate that the proposed framework can produce retargeted motions for three different characters – a quadrupedal robot with a manipulator, a crab character, and a wheeled manipulator. We further validate the design choices of our framework by conducting baseline comparisons and a user study. We also showcase sim-to-real transfer of the retargeted motions by transferring them to a real Spot robot.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“While these studies have successfully demonstrated motion retargeting from humanoid to non-humanoid morphologies, they often rely on either embodiment-specific or task-specific models.”
From LEGATO: Cross-Embodiment Imitation Using a Grasping Tool (2025) · cites this paper as [33]
Citations
The citation lists are queued
They are fetched later and appear here then.
References 28 · Cited by 18
Research works printed but not linked: 10
- Michel Abdul-Massih, Innfarn Yoo, and Bedrich Benes. 2017. Motion style retargeting to characters with different morphologies. In Computer Graphics Forum, Vol. 36. Wiley Online Library, 86–99.
- Noam Aigerman, Kunal Gupta, Vladimir G Kim, Siddhartha Chaudhuri, Jun Saito, and Thibault Groueix. 2022. Neural jacobian fields: Learning intrinsic mappings of arbitrary meshes. arXiv preprint arXiv:2205.02904 (2022). · arXiv
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
- Tianyu Li, Jungdam Won, Sehoon Ha, and Akshara Rai. 2021b. FastMimic: Model-based Motion Imitation for Agile, Diverse and Generalizable Quadrupedal Locomotion. arXiv preprint arXiv:2109.13362 (2021). · arXiv
- Lars Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which training methods for GANs do actually converge?. In International conference on machine learning. PMLR, 3481–3490.
- Xue Bin Peng, Michael Chang, Grace Zhang, Pieter Abbeel, and Sergey Levine. 2019. Mcp: Learning composable hierarchical control with multiplicative compositional policies. Advances in Neural Information Processing Systems 32 (2019).
- Xue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine, and Sanja Fidler. 2022. ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters. arXiv preprint arXiv:2205.01906 (2022). · arXiv
- Ahmad Rashid, Alan Do-Omri, Md Haidar, Qun Liu, Mehdi Rezagholizadeh, 2019. Bilingual-gan: A step towards parallel text generation. arXiv preprint arXiv:1904.04742 (2019). · arXiv
- Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. 2022. Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022). · arXiv
- 10.5555/1921427.1921453 · doi:10.5555/1921427.1921453
Metadata
- Authors
- Li, T., Won, J., Clegg, A., Kim, J., Rai, A., & Ha, S.
- Affiliations
- Georgia Institute of Technology (US)
- Seoul National University (KR)
- Meta (United States) (US)
- Venue
- SIGGRAPH Asia 2023 Conference Papers
- Publisher
- ACM
- Published
- 2023-12-10
- Pages
- 1-11
- OpenAlex
- W4389539433
- Cited by
- 18
- References
- 28
- Citations by year
- 2026: 2 · 2025: 8 · 2024: 8
- FWCI
- 7.71
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- SIGGRAPH Asia Conference Papers (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- Seoul National University Open Repository (Seoul National University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Meta
- NSF: FW-HTF-P: Reshaping Construction Work Conventions: Endowing Collaborative Construction Robots with Social Intelligence for Contextually-Appropriate Robot Behaviors (2222723)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- motion retargeting, generative adversarial networks, feature loss, quadrupedal robots, sim-to-real transfer, Spot robot
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: ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters. https://app.cochat.ai/papers/10.1145/3610548.3618255
- The paper
- Li, T., Won, J., Clegg, A., Kim, J., Rai, A., & Ha, S. (2023). ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters. SIGGRAPH Asia 2023 Conference Papers. https://doi.org/10.1145/3610548.3618255
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.