# WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds

arXiv: https://arxiv.org/abs/2407.18946 · HTML: https://mlsanity.com/paper/2407.18946/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 11 Jul 2024.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [Neural Kinematic Networks for Unsupervised Motion Retargetting](https://mlsanity.com/paper/1804.05653/) (2018)
- [Motion In-Betweening with Phase Manifolds](https://mlsanity.com/paper/2308.12751/) (2023)
- [ACE: Adversarial Correspondence Embedding for Cross Morphology Motion Retargeting from Human to Nonhuman Characters](https://mlsanity.com/paper/2305.14792/) (2023)
- [MOCHA: Real-Time Motion Characterization via Context Matching](https://mlsanity.com/paper/2310.10079/) (2023)

## Built on by (most cited first, 14 of 14)

- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence](https://mlsanity.com/paper/2508.13139/) (2025)
- [Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion](https://mlsanity.com/paper/2503.19557/) (2025)
- [MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning](https://mlsanity.com/paper/2411.16964/) (2024)
- [X-MoGen: Unified Motion Generation across Humans and Animals](https://mlsanity.com/paper/2508.05162/) (2025)
- [Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation](https://mlsanity.com/paper/2503.08180/) (2025)
- [MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matching](https://mlsanity.com/paper/2509.25600/) (2025)
- [DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing](https://mlsanity.com/paper/2605.28491/) (2026)
- [SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology](https://mlsanity.com/paper/2607.02148/) (2026)
- [FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds](https://mlsanity.com/paper/2512.09423/) (2025)
- [Controllable Text-to-Motion Generation via Modular Body-Part Phase Control](https://mlsanity.com/paper/2603.19795/) (2026)
- [AnyAct: Towards Human Reenactment of Character Motion From Video](https://mlsanity.com/paper/2605.15497/) (2026)
- [Two2Four: Generative Quadruped Puppeteering from Human Motion](https://mlsanity.com/paper/2607.26108/) (2026)
- [STyMo: Fast and Controllable Few-Shot Motion Style Transfer](https://mlsanity.com/paper/2609.04500/) (2026)

## Abstract (arXiv)

We present a new approach for understanding the periodicity structure and semantics of motion datasets, independently of the morphology and skeletal structure of characters. Unlike existing methods using an overly sparse high-dimensional latent, we propose a phase manifold consisting of multiple closed curves, each corresponding to a latent amplitude. With our proposed vector quantized periodic autoencoder, we learn a shared phase manifold for multiple characters, such as a human and a dog, without any supervision. This is achieved by exploiting the discrete structure and a shallow network as bottlenecks, such that semantically similar motions are clustered into the same curve of the manifold, and the motions within the same component are aligned temporally by the phase variable. In combination with an improved motion matching framework, we demonstrate the manifold's capability of timing and semantics alignment in several applications, including motion retrieval, transfer and stylization. Code and pre-trained models for this paper are available at https://peizhuoli.github.io/walkthedog.