# MoGlow: Probabilistic and controllable motion synthesis using normalising flows

arXiv: https://arxiv.org/abs/1905.06598 · HTML: https://mlsanity.com/paper/1905.06598/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2019.

## Built on by (most cited first, 30 of 47)

- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering](https://mlsanity.com/paper/2109.08379/) (2021)
- [Synthesis of Compositional Animations from Textual Descriptions](https://mlsanity.com/paper/2103.14675/) (2021)
- [Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion](https://mlsanity.com/paper/2204.08451/) (2022)
- [Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation](https://mlsanity.com/paper/2401.08559/) (2024)
- [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)
- [UDE: A Unified Driving Engine for Human Motion Generation](https://mlsanity.com/paper/2211.16016/) (2022)
- [A Comprehensive Review of Data-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2301.05339/) (2023)
- [MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations](https://mlsanity.com/paper/2310.10198/) (2023)
- [Taming Diffusion Probabilistic Models for Character Control](https://mlsanity.com/paper/2404.15121/) (2024)
- [CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis](https://mlsanity.com/paper/2303.15469/) (2023)
- [TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis](https://mlsanity.com/paper/2307.15042/) (2023)
- [Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion](https://mlsanity.com/paper/2312.04466/) (2023)
- [Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings](https://mlsanity.com/paper/2210.01448/) (2022)
- [Neural Categorical Priors for Physics-Based Character Control](https://mlsanity.com/paper/2308.07200/) (2023)
- [Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation](https://mlsanity.com/paper/2109.10595/) (2021)
- [Task-Generic Hierarchical Human Motion Prior using VAEs](https://mlsanity.com/paper/2106.04004/) (2021)
- [HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device](https://mlsanity.com/paper/2409.13426/) (2024)
- [Conditional Motion In-betweening](https://mlsanity.com/paper/2202.04307/) (2022)
- [GANimator: Neural Motion Synthesis from a Single Sequence](https://mlsanity.com/paper/2205.02625/) (2022)
- [Transflower: probabilistic autoregressive dance generation with multimodal attention](https://mlsanity.com/paper/2106.13871/) (2021)
- [DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model](https://mlsanity.com/paper/2301.10047/) (2023)
- [BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer](https://mlsanity.com/paper/2310.06851/) (2023)
- [What is the Best Automated Metric for Text to Motion Generation?](https://mlsanity.com/paper/2309.10248/) (2023)
- [Action-conditioned On-demand Motion Generation](https://mlsanity.com/paper/2207.08164/) (2022)
- [Integrated Speech and Gesture Synthesis](https://mlsanity.com/paper/2108.11436/) (2021)
- [Example-based Motion Synthesis via Generative Motion Matching](https://mlsanity.com/paper/2306.00378/) (2023)
- [Generating coherent spontaneous speech and gesture from text](https://mlsanity.com/paper/2101.05684/) (2021)
- [Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech](https://mlsanity.com/paper/2106.14736/) (2021)

## Abstract (arXiv)

Data-driven modelling and synthesis of motion is an active research area with applications that include animation, games, and social robotics. This paper introduces a new class of probabilistic, generative, and controllable motion-data models based on normalising flows. Models of this kind can describe highly complex distributions, yet can be trained efficiently using exact maximum likelihood, unlike GANs or VAEs. Our proposed model is autoregressive and uses LSTMs to enable arbitrarily long time-dependencies. Importantly, is is also causal, meaning that each pose in the output sequence is generated without access to poses or control inputs from future time steps; this absence of algorithmic latency is important for interactive applications with real-time motion control. The approach can in principle be applied to any type of motion since it does not make restrictive, task-specific assumptions regarding the motion or the character morphology. We evaluate the models on motion-capture datasets of human and quadruped locomotion. Objective and subjective results show that randomly-sampled motion from the proposed method outperforms task-agnostic baselines and attains a motion quality close to recorded motion capture.