# Motion In-Betweening with Phase Manifolds

arXiv: https://arxiv.org/abs/2308.12751 · HTML: https://mlsanity.com/paper/2308.12751/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 38 references that are in the map.
- First posted on arXiv 24 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [Simulation and Retargeting of Complex Multi-Character Interactions](https://mlsanity.com/paper/2305.20041/) (2023)
- [Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling](https://mlsanity.com/paper/1908.07214/) (2019)
- [Real-time Controllable Motion Transition for Characters](https://mlsanity.com/paper/2205.02540/) (2022)
- [Animating Human Athletics](https://mlsanity.com/paper/2302.06108/) (2023)

## Built on by (most cited first, 25 of 25)

- [Seamless Human Motion Composition with Blended Positional Encodings](https://mlsanity.com/paper/2402.15509/) (2024)
- [M3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation](https://mlsanity.com/paper/2405.16273/) (2024)
- [FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning](https://mlsanity.com/paper/2402.13820/) (2024)
- [RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards](https://mlsanity.com/paper/2407.11562/) (2024)
- [Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation](https://mlsanity.com/paper/2504.19189/) (2025)
- [Simulating the Real World: A Unified Survey of Multimodal Generative Models](https://mlsanity.com/paper/2503.04641/) (2025)
- [WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds](https://mlsanity.com/paper/2407.18946/) (2024)
- [AAMDM: Accelerated Auto-regressive Motion Diffusion Model](https://mlsanity.com/paper/2401.06146/) (2023)
- [MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning](https://mlsanity.com/paper/2411.16964/) (2024)
- [Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion](https://mlsanity.com/paper/2505.11013/) (2025)
- [Deep Compositional Phase Diffusion for Long Motion Sequence Generation](https://mlsanity.com/paper/2510.14427/) (2025)
- [MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives](https://mlsanity.com/paper/2604.24833/) (2026)
- [Real-time Diverse Motion In-betweening with Space-time Control](https://mlsanity.com/paper/2410.00270/) (2024)
- [HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA](https://mlsanity.com/paper/2511.01463/) (2025)
- [Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation](https://mlsanity.com/paper/2503.08180/) (2025)
- [Motion Generation Review: Exploring Deep Learning for Lifelike Animation with Manifold](https://mlsanity.com/paper/2412.10458/) (2024)
- [SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach](https://mlsanity.com/paper/2506.09075/) (2025)
- [ExoGait-MS: Learning Periodic Dynamics with Multi-Scale Graph Network for Exoskeleton Gait Recognition](https://mlsanity.com/paper/2505.18018/) (2025)
- [Generating Detailed Character Motion from Blocking Poses](https://mlsanity.com/paper/2509.16064/) (2025)
- [Motion In-Betweening for Densely Interacting Characters](https://mlsanity.com/paper/2510.00314/) (2025)
- [FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds](https://mlsanity.com/paper/2512.09423/) (2025)
- [Dancing Points: Synthesizing Ballroom Dancing with Three-Point Inputs](https://mlsanity.com/paper/2601.02096/) (2026)
- [SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonization](https://mlsanity.com/paper/2602.04271/) (2026)
- [Generative Motion In-betweening by Diffusion over Continuous Implicit Representations](https://mlsanity.com/paper/2605.12778/) (2026)
- [Progressively Learning Heterogeneous Skills in a Unified Latent Space](https://mlsanity.com/paper/2608.23258/) (2026)

## Abstract (arXiv)

This paper introduces a novel data-driven motion in-betweening system to reach target poses of characters by making use of phases variables learned by a Periodic Autoencoder. Our approach utilizes a mixture-of-experts neural network model, in which the phases cluster movements in both space and time with different expert weights. Each generated set of weights then produces a sequence of poses in an autoregressive manner between the current and target state of the character. In addition, to satisfy poses which are manually modified by the animators or where certain end effectors serve as constraints to be reached by the animation, a learned bi-directional control scheme is implemented to satisfy such constraints. The results demonstrate that using phases for motion in-betweening tasks sharpen the interpolated movements, and furthermore stabilizes the learning process. Moreover, using phases for motion in-betweening tasks can also synthesize more challenging movements beyond locomotion behaviors. Additionally, style control is enabled between given target keyframes. Our proposed framework can compete with popular state-of-the-art methods for motion in-betweening in terms of motion quality and generalization, especially in the existence of long transition durations. Our framework contributes to faster prototyping workflows for creating animated character sequences, which is of enormous interest for the game and film industry.