# Hierarchical Style-based Networks for Motion Synthesis

arXiv: https://arxiv.org/abs/2008.10162 · HTML: https://mlsanity.com/paper/2008.10162/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Synthesis of Compositional Animations from Textual Descriptions](https://mlsanity.com/paper/2103.14675/) (2021)
- [COUCH: Towards Controllable Human-Chair Interactions](https://mlsanity.com/paper/2205.00541/) (2022)
- [Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis](https://mlsanity.com/paper/2205.13001/) (2022)
- [Full-Body Articulated Human-Object Interaction](https://mlsanity.com/paper/2212.10621/) (2022)
- [F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions](https://mlsanity.com/paper/2407.12435/) (2024)
- [ROAM: Robust and Object-Aware Motion Generation Using Neural Pose Descriptors](https://mlsanity.com/paper/2308.12969/) (2023)
- [Scene Synthesis from Human Motion](https://mlsanity.com/paper/2301.01424/) (2023)
- [Action2video: Generating Videos of Human 3D Actions](https://mlsanity.com/paper/2111.06925/) (2021)
- [Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes](https://mlsanity.com/paper/2209.06314/) (2022)
- [3D Human Interaction Generation: A Survey](https://mlsanity.com/paper/2503.13120/) (2025)
- [StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion](https://mlsanity.com/paper/2503.21775/) (2025)
- [Learning Disentangled Representations for Controllable Human Motion Prediction](https://mlsanity.com/paper/2207.01388/) (2022)
- [OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression](https://mlsanity.com/paper/2510.14954/) (2025)
- [Learning Setup Policies: Reliable Transition Between Locomotion Behaviours](https://mlsanity.com/paper/2101.09391/) (2021)
- [Diverse Motion In-betweening with Dual Posture Stitching](https://mlsanity.com/paper/2303.14457/) (2023)
- [MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow](https://mlsanity.com/paper/2412.09901/) (2024)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [HEIR: Learning Graph-Based Motion Hierarchies](https://mlsanity.com/paper/2510.26786/) (2025)
- [ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation](https://mlsanity.com/paper/2512.02453/) (2025)
- [PACE: Data-Driven Virtual Agent Interaction in Dense and Cluttered Environments](https://mlsanity.com/paper/2303.14255/) (2023)
- [DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception](https://mlsanity.com/paper/2403.01740/) (2024)

## Abstract (arXiv)

Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world. In this paper, we propose a self-supervised method for generating long-range, diverse and plausible behaviors to achieve a specific goal location. Our proposed method learns to model the motion of human by decomposing a long-range generation task in a hierarchical manner. Given the starting and ending states, a memory bank is used to retrieve motion references as source material for short-range clip generation. We first propose to explicitly disentangle the provided motion material into style and content counterparts via bi-linear transformation modelling, where diverse synthesis is achieved by free-form combination of these two components. The short-range clips are then connected to form a long-range motion sequence. Without ground truth annotation, we propose a parameterized bi-directional interpolation scheme to guarantee the physical validity and visual naturalness of generated results. On large-scale skeleton dataset, we show that the proposed method is able to synthesise long-range, diverse and plausible motion, which is also generalizable to unseen motion data during testing. Moreover, we demonstrate the generated sequences are useful as subgoals for actual physical execution in the animated world.