Paper overview · author-verified

InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild

Authors: Yiyi Ma, , Xiu Li, Chi Zhang, Xuelong Li

IEEE/CVF International Conference on Computer Vision (ICCV 2025) · 2025 · pp. 12832-12841

3D human motionmulti-person interactioninterleaved learningmotion synthesiscoordination refinement

Publication details

Authors
Yiyi Ma, Yuanzhi Liang, Xiu Li, Chi Zhang, and Xuelong Li
Recommended paper citation
Yiyi Ma, Yuanzhi Liang, Xiu Li, Chi Zhang, and Xuelong Li. “InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild.” 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (2025), 12832-12841. https://doi.org/10.1109/ICCV51701.2025.01192.

Version dates

arXiv first posted
2025-08-14
arXiv last revised
2025-08-14
Source checked
2026-07-31
Verification status
Author-verified on 2026-07-31

Summary

InterSyn learns solo and multi-person dynamics together rather than treating them as separate tasks: INS synthesizes both from a first-person interaction perspective, and REC refines relative coordination so characters move synchronously.

Research paths

How this paper contributes to the site's broader research map.

Research question

Separating solo motion from multi-person interaction makes it difficult to learn how individual behavior and mutual coordination combine in realistic, dynamic interactions.

What the paper contributes

  • Uses interleaved learning over integrated solo and multi-person motions.
  • Introduces Interleaved Interaction Synthesis (INS) to jointly model solo and interactive behavior from a first-person perspective.
  • Introduces Relative Coordination Refinement (REC) to refine mutual dynamics and synchronization.

Evidence and evaluation scope

The paper reports higher text-to-motion alignment and greater diversity than recent comparison methods. The claim concerns the evaluated motion-synthesis setup; exact datasets, baselines, and scores should be cited from the ICCV paper.

Scope and limitations

The demonstrated scope is motion synthesis from integrated solo and multi-person data. The abstract does not establish generality to arbitrary numbers of people, environments, or interaction semantics outside the evaluated distributions.

Positioning for related work

InterSyn is a multi-person interaction-motion method centered on integrated learning and relative coordination. It should not be described as a method for learning motion jointly with a dynamic environment; its 'dynamic' aspect refers to solo and interacting character dynamics.

Related-work context

Ma et al. propose InterSyn, which interleaves solo and multi-person motion learning through an interaction-synthesis module and refines relative coordination to improve synchronized, text-aligned interaction motion.

A concise, neutral description of how this paper can be situated in related work.

Official abstract

We present Interleaved Learning for Motion Synthesis (InterSyn), a novel framework that targets the generation of realistic interaction motions by learning from integrated motions that consider both solo and multi-person dynamics. Unlike previous methods that treat these components separately, InterSyn employs an interleaved learning strategy to capture the natural, dynamic interactions and nuanced coordination inherent in real-world scenarios. Our framework comprises two key modules: the Interleaved Interaction Synthesis (INS) module, which jointly models solo and interactive behaviors in a unified paradigm from a first-person perspective to support multiple character interactions, and the Relative Coordination Refinement (REC) module, which refines mutual dynamics and ensures synchronized motions among characters. Experimental results show that the motion sequences generated by InterSyn exhibit higher text-to-motion alignment and improved diversity compared with recent methods, setting a new benchmark for robust and natural motion synthesis. Additionally, our code will be open-sourced in the future to promote further research and development in this area.

The abstract is reproduced for scholarly identification and remains under the paper publisher/authors’ original copyright; it is not covered by this page’s CC BY license.

Evidence references

What to verifyLocation in the paper
Problem statementAbstract
Method and contributionsAbstract; INS and REC method sections
Evaluation statementAbstract; text-to-motion alignment and diversity experiments

Primary source: IEEE version of record (ICCV 2025 version of record; CVF open-access copy and arXiv:2508.10297v1 cross-checked).

How to cite

Cite the paper—not this explainer—for scientific claims. Cite this page only when reusing its original commentary.

Yiyi Ma, Yuanzhi Liang, Xiu Li, Chi Zhang, and Xuelong Li. “InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild.” 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (2025), 12832-12841. https://doi.org/10.1109/ICCV51701.2025.01192.

Reuse policy

Original explanatory text on this page is licensed under CC BY 4.0 with attribution and a link to this page. Paper title, abstract, figures, and bibliographic metadata are excluded and retain their original rights. Creative Commons Attribution 4.0 International.

Primary sources and resources