# Motion In-Betweening for Densely Interacting Characters

arXiv: https://arxiv.org/abs/2510.00314 · HTML: https://mlsanity.com/paper/2510.00314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 55 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases](https://mlsanity.com/paper/2201.04439/) (2022)
- [Flexible Motion In-betweening with Diffusion Models](https://mlsanity.com/paper/2405.11126/) (2024)
- [ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions](https://mlsanity.com/paper/2311.17057/) (2023)
- [Recurrent Transition Networks for Character Locomotion](https://mlsanity.com/paper/1810.02363/) (2018)
- [Interaction Transformer for Human Reaction Generation](https://mlsanity.com/paper/2207.01685/) (2022)
- [Simulation and Retargeting of Complex Multi-Character Interactions](https://mlsanity.com/paper/2305.20041/) (2023)
- [Real-time Controllable Motion Transition for Characters](https://mlsanity.com/paper/2205.02540/) (2022)
- [Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation](https://mlsanity.com/paper/2502.20370/) (2025)
- [Conditional Motion In-betweening](https://mlsanity.com/paper/2202.04307/) (2022)
- [Motion In-Betweening with Phase Manifolds](https://mlsanity.com/paper/2308.12751/) (2023)
- [RSMT: Real-time Stylized Motion Transition for Characters](https://mlsanity.com/paper/2306.11970/) (2023)
- [Motion Inbetweening via Deep Delta-Interpolator](https://mlsanity.com/paper/2201.06701/) (2022)
- [Dyadic Human Motion Prediction](https://mlsanity.com/paper/2112.00396/) (2021)
- [Real-time Diverse Motion In-betweening with Space-time Control](https://mlsanity.com/paper/2410.00270/) (2024)
- [Generative Motion Infilling From Imprecisely Timed Keyframes](https://mlsanity.com/paper/2503.01016/) (2025)

## Abstract (arXiv)

Motion in-betweening is the problem to synthesize movement between keyposes. Traditional research focused primarily on single characters. Extending them to densely interacting characters is highly challenging, as it demands precise spatial-temporal correspondence between the characters to maintain the interaction, while creating natural transitions towards predefined keyposes. In this research, we present a method for long-horizon interaction in-betweening that enables two characters to engage and respond to one another naturally. To effectively represent and synthesize interactions, we propose a novel solution called Cross-Space In-Betweening, which models the interactions of each character across different conditioning representation spaces. We further observe that the significantly increased constraints in interacting characters heavily limit the solution space, leading to degraded motion quality and diminished interaction over time. To enable long-horizon synthesis, we present two solutions to maintain long-term interaction and motion quality, thereby keeping synthesis in the stable region of the solution space.We first sustain interaction quality by identifying periodic interaction patterns through adversarial learning. We further maintain the motion quality by learning to refine the drifted latent space and prevent pose error accumulation. We demonstrate that our approach produces realistic, controllable, and long-horizon in-between motions of two characters with dynamic boxing and dancing actions across multiple keyposes, supported by extensive quantitative evaluations and user studies.