mlsanityData to 14 Oct 2026

Conditional Motion In-betweening

arXiv 2202.04307 ↗First posted 9 Feb 2022cs.CV cs.AI cs.GRcited by 25

Not on the map. Why?

Abstract (arXiv)

Motion in-betweening (MIB) is a process of generating intermediate skeletal movement between the given start and target poses while preserving the naturalness of the motion, such as periodic footstep motion while walking. Although state-of-the-art MIB methods are capable of producing plausible motions given sparse key-poses, they often lack the controllability to generate motions satisfying the semantic contexts required in practical applications. We focus on the method that can handle pose or semantic conditioned MIB tasks using a unified model. We also present a motion augmentation method to improve the quality of pose-conditioned motion generation via defining a distribution over smooth trajectories. Our proposed method outperforms the existing state-of-the-art MIB method in pose prediction errors while providing additional controllability.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 9 Feb 2022.

Builds on

28 of 55 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  4. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  5. 2016Least Squares Generative Adversarial Networkscited by 1,001
  6. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  7. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  8. 2017Convolutional Sequence to Sequence Learningcited by 552
  9. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  10. 2017On human motion prediction using recurrent neural networkscited by 338
  11. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  12. 2019Depth-Aware Video Frame Interpolationcited by 234
16 more
  1. 2021Robust Motion In-betweeningcited by 229
  2. 2021Character Controllers Using Motion VAEscited by 184
  3. 2020Learning Joint Spatial-Temporal Transformations for Video Inpaintingcited by 163
  4. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  5. 2017Text2Action: Generative Adversarial Synthesis from Language to Actioncited by 106
  6. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  7. 2020Unpaired Motion Style Transfer from Video to Animationcited by 94
  8. 2020Convolutional Autoencoders for Human Motion Infillingcited by 73
  9. 2017Learning Human Motion Models for Long-term Predictionscited by 67
  10. 2014Learning Stochastic Recurrent Networkscited by 60
  11. 2021Single-Shot Motion Completion with Transformercited by 59
  12. 2018Recurrent Transition Networks for Character Locomotioncited by 52
  13. 2019MoGlow: Probabilistic and controllable motion synthesis using normalising flowscited by 47
  14. 2021Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformerscited by 46
  15. 2019Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modelingcited by 32
  16. 2021HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Mediacited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 2; 2025: 9; 2026: 4.

25 papers.

Sort:

By area:

  1. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  2. 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
  3. 2024Seamless Human Motion Composition with Blended Positional Encodingscited by 80
  4. 2025HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videoscited by 66
  5. 2023SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generationcited by 64
  6. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  7. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Modelscited by 55
  8. 2023Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusioncited by 39
  9. 2025SceneMI: Motion In-betweening for Modeling Human-Scene Interactionscited by 11
  10. 2024Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformercited by 9
  11. 2025Motion Synthesis with Sparse and Flexible Keyjoint Controlcited by 9
  12. 2025Deep Compositional Phase Diffusion for Long Motion Sequence Generationcited by 6
13 more
  1. 2026MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitivescited by 6
  2. 2023A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesiscited by 4
  3. 2023Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Predictioncited by 4
  4. 2022Learning Joint Representation of Human Motion and Languagecited by 3
  5. 2023Diverse Motion In-betweening with Dual Posture Stitchingcited by 2
  6. 2025SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approachcited by 1
  7. 2025A Plug-and-Play Multi-Criteria Guidance for Diverse In-Betweening Human Motion Generationcited by 1
  8. 2026Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregationcited by 1
  9. 2025PMG: Progressive Motion Generation via Sparse Anchor Postures Curriculum Learningcited by 0
  10. 2025From Motion to Behavior: Hierarchical Modeling of Humanoid Generative Behavior Controlcited by 0
  11. 2025Motion In-Betweening for Densely Interacting Characterscited by 0
  12. 2026Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animationcited by 0
  13. 2026Generative Motion In-betweening by Diffusion over Continuous Implicit Representationscited by 0