# Graph-based Normalizing Flow for Human Motion Generation and Reconstruction

arXiv: https://arxiv.org/abs/2104.03020 · HTML: https://mlsanity.com/paper/2104.03020/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 20 of 20)

- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Structural-RNN: Deep Learning on Spatio-Temporal Graphs](https://mlsanity.com/paper/1511.05298/) (2015)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [Graph Normalizing Flows](https://mlsanity.com/paper/1905.13177/) (2019)
- [Deep representation learning for human motion prediction and classification](https://mlsanity.com/paper/1702.07486/) (2017)
- [Gesticulator: A framework for semantically-aware speech-driven gesture generation](https://mlsanity.com/paper/2001.09326/) (2020)
- [Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Control](https://mlsanity.com/paper/1806.08666/) (2018)
- [Part-based Graph Convolutional Network for Action Recognition](https://mlsanity.com/paper/1809.04983/) (2018)
- [Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model](https://mlsanity.com/paper/2010.09950/) (2020)
- [Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music](https://mlsanity.com/paper/1911.04069/) (2019)
- [Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization](https://mlsanity.com/paper/2012.02043/) (2020)
- [A Deep Recurrent Framework for Cleaning Motion Capture Data](https://mlsanity.com/paper/1712.03380/) (2017)

## Built on by (most cited first, 12 of 12)

- [Normalizing Flows for Human Pose Anomaly Detection](https://mlsanity.com/paper/2211.10946/) (2022)
- [Interaction Transformer for Human Reaction Generation](https://mlsanity.com/paper/2207.01685/) (2022)
- [Dance Style Transfer with Cross-modal Transformer](https://mlsanity.com/paper/2208.09406/) (2022)
- [Bipartite Graph Diffusion Model for Human Interaction Generation](https://mlsanity.com/paper/2301.10134/) (2023)
- [Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion Models](https://mlsanity.com/paper/2304.04681/) (2023)
- [Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows](https://mlsanity.com/paper/2404.17381/) (2024)
- [Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction](https://mlsanity.com/paper/2503.06119/) (2025)
- [Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward](https://mlsanity.com/paper/2506.03191/) (2025)
- [ST-GDance: Long-Term and Collision-Free Group Choreography from Music](https://mlsanity.com/paper/2507.21518/) (2025)
- [Evaluating the Evaluators: Towards Human-aligned Metrics for Missing Markers Reconstruction](https://mlsanity.com/paper/2410.14334/) (2024)
- [Sparse Compositional Flow Matching by geometric assembly from motion primitives](https://mlsanity.com/paper/2605.23341/) (2026)
- [Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction](https://mlsanity.com/paper/2608.21093/) (2026)

## Abstract (arXiv)

Data-driven approaches for modeling human skeletal motion have found various applications in interactive media and social robotics. Challenges remain in these fields for generating high-fidelity samples and robustly reconstructing motion from imperfect input data, due to e.g. missed marker detection. In this paper, we propose a probabilistic generative model to synthesize and reconstruct long horizon motion sequences conditioned on past information and control signals, such as the path along which an individual is moving. Our method adapts the existing work MoGlow by introducing a new graph-based model. The model leverages the spatial-temporal graph convolutional network (ST-GCN) to effectively capture the spatial structure and temporal correlation of skeletal motion data at multiple scales. We evaluate the models on a mixture of motion capture datasets of human locomotion with foot-step and bone-length analysis. The results demonstrate the advantages of our model in reconstructing missing markers and achieving comparable results on generating realistic future poses. When the inputs are imperfect, our model shows improvements on robustness of generation.