mlsanityData to 14 Oct 2026

Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases

arXiv 2201.04439 ↗First posted 12 Jan 2022cs.GR cs.AI cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

Controlling the manner in which a character moves in a real-time animation system is a challenging task with useful applications. Existing style transfer systems require access to a reference content motion clip, however, in real-time systems the future motion content is unknown and liable to change with user input. In this work we present a style modelling system that uses an animation synthesis network to model motion content based on local motion phases. An additional style modulation network uses feature-wise transformations to modulate style in real-time. To evaluate our method, we create and release a new style modelling dataset, 100STYLE, containing over 4 million frames of stylised locomotion data in 100 different styles that present a number of challenges for existing systems. To model these styles, we extend the local phase calculation with a contact-free formulation. In comparison to other methods for real-time style modelling, we show our system is more robust and efficient in its style representation while improving motion quality.

Key facts. Cited by 72 papers in the map (data through 14 Oct 2026). Builds on 23 of its 63 references that are in the map. First posted on arXiv 12 Jan 2022.

Builds on

23 of 63 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  4. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  5. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  6. 2017Learning multiple visual domains with residual adapterscited by 557
  7. 2015A Neural Algorithm of Artistic Stylecited by 483
  8. 2016A Learned Representation For Artistic Stylecited by 341
  9. 2017On human motion prediction using recurrent neural networkscited by 338
  10. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  11. 2021Character Controllers Using Motion VAEscited by 184
  12. 2018Efficient parametrization of multi-domain deep neural networkscited by 168
11 more
  1. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  2. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 124
  3. 2017Deep representation learning for human motion prediction and classificationcited by 98
  4. 2020Unpaired Motion Style Transfer from Video to Animationcited by 94
  5. 2018Learning Symmetric and Low-energy Locomotioncited by 61
  6. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  7. 2019MoGlow: Probabilistic and controllable motion synthesis using normalising flowscited by 47
  8. 2020Source Free Domain Adaptation with Image Translationcited by 21
  9. 2021Test Sample Accuracy Scales with Training Sample Density in Neural Networkscited by 9
  10. 2017Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesiscited by 6
  11. 2019Customizing Sequence Generation with Multi-Task Dynamical Systemscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 8; 2024: 11; 2025: 28; 2026: 20.

72 papers.

Sort:

By area:

  1. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 190
  2. 2023Human Motion Generation: A Surveycited by 96
  3. 2024MotionFix: Text-Driven 3D Human Motion Editingcited by 64
  4. 2024Taming Diffusion Probabilistic Models for Character Controlcited by 57
  5. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Modelscited by 55
  6. 2024ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Modelcited by 53
  7. 2023TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesiscited by 49
  8. 2023OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllerscited by 47
  9. 2024SMooDi: Stylized Motion Diffusion Modelcited by 37
  10. 2025HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generationcited by 36
  11. 2022Pretrained Diffusion Models for Unified Human Motion Synthesiscited by 26
  12. 2025A Survey on Human Interaction Motion Generationcited by 25
38 more
  1. 2022GANimator: Neural Motion Synthesis from a Single Sequencecited by 23
  2. 2025The Quest for Generalizable Motion Generation: Data, Model, and Evaluationcited by 22
  3. 2022Dance Style Transfer with Cross-modal Transformercited by 20
  4. 2023RSMT: Real-time Stylized Motion Transition for Characterscited by 19
  5. 2025PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction Systemcited by 18
  6. 2025Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusioncited by 16
  7. 2025SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Controlcited by 15
  8. 2025PersonaBooth: Personalized Text-to-Motion Generationcited by 14
  9. 2024SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generationcited by 12
  10. 2026LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokenscited by 11
  11. 2024Generative Motion Stylization of Cross-structure Characters within Canonical Motion Spacecited by 10
  12. 2023Motion Capture Dataset for Practical Use of AI-based Motion Editing and Stylizationcited by 9
  13. 2025Motion Generation: A Survey of Generative Approaches and Benchmarkscited by 8
  14. 2024Diffusion-based Human Motion Style Transfer with Semantic Guidancecited by 7
  15. 2025StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusioncited by 7
  16. 2026EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videoscited by 7
  17. 2025Deep Compositional Phase Diffusion for Long Motion Sequence Generationcited by 6
  18. 2025UniMoGen: Universal Motion Generationcited by 5
  19. 2025MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editingcited by 5
  20. 2026Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Controlcited by 5
  21. 2023Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phasecited by 4
  22. 2023Scalable Motion Style Transfer with Constrained Diffusion Generationcited by 4
  23. 2024Decoupling Contact for Fine-Grained Motion Style Transfercited by 4
  24. 2024Real-time Diverse Motion In-betweening with Space-time Controlcited by 4
  25. 2025SMooGPT: Stylized Motion Generation using Large Language Modelscited by 4
  26. 2025OmniMotion-X: Versatile Multimodal Whole-Body Motion Generationcited by 4
  27. 2024SMGDiff: Soccer Motion Generation using diffusion probabilistic modelscited by 3
  28. 2025Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representationcited by 3
  29. 2025PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Taskscited by 3
  30. 2026VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representationscited by 3
  31. 2024MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flowcited by 2
  32. 2025ASMR: Adaptive Skeleton-Mesh Rigging and Skinning via 2D Generative Priorcited by 2
  33. 2025Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognitioncited by 2
  34. 2026ReActor: Reinforcement Learning for Physics-Aware Motion Retargetingcited by 2
  35. 2026Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priorscited by 2
  36. 2026Scaling Behavior Foundation Model for Humanoid Robotscited by 2
  37. 2025ACMo: Attribute Controllable Motion Generationcited by 1
  38. 2025RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characterscited by 1

50 most cited of 72 All 72 (JSON)