mlsanityData to 14 Oct 2026

Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach

arXiv 2512.16456 ↗First posted 18 Dec 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Human motion generation is a challenging task that aims to create realistic motion imitating natural human behaviour. We focus on the well-studied behaviour of priming an object/location for pick up or put down - that is, the spotting of an object/location from a distance, known as gaze priming, followed by the motion of approaching and reaching the target location. To that end, we curate, for the first time, 23.7K gaze-primed human motion sequences for reaching target object locations from five publicly available datasets, i.e., HD-EPIC, MoGaze, HOT3D, ADT, and GIMO. We pre-train a text-conditioned diffusion-based motion generation model, then fine-tune it conditioned on goal pose or location, on our curated sequences. Importantly, we evaluate the ability of the generated motion to imitate natural human movement through several metrics, including the 'Reach Success' and a newly introduced 'Prime Success' metric. Tested on 5 datasets, our model generates diverse full-body motion, exhibiting both priming and reaching behaviour, and outperforming baselines and recent methods.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 89 of its 102 references that are in the map. First posted on arXiv 18 Dec 2025.

Builds on

89 of 102 references.

References · 89

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  6. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  7. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  8. 2022Human Motion Diffusion Modelcited by 1,080
  9. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  10. 2023T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representationscited by 588
  11. 2020Rescaling Egocentric Visioncited by 540
  12. 2023MotionGPT: Human Motion as a Foreign Languagecited by 527
38 more
  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  2. 2022TEMOS: Generating diverse human motions from textual descriptionscited by 492
  3. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 490
  4. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 485
  5. 2020Action2Motion: Conditioned Generation of 3D Human Motionscited by 441
  6. 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 405
  7. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 400
  8. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  9. 2022EDGE: Editable Dance Generation From Musiccited by 287
  10. 2023ReMoDiffuse: Retrieval-Augmented Motion Diffusion Modelcited by 287
  11. 2019Language2Pose: Natural Language Grounded Pose Forecastingcited by 257
  12. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 238
  13. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 223
  14. 2022FLAME: Free-form Language-based Motion Synthesis & Editingcited by 217
  15. 2023Project Aria: A New Tool for Egocentric Multi-Modal AI Researchcited by 208
  16. 2023TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesiscited by 198
  17. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 190
  18. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 182
  19. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
  20. 2022TEACH: Temporal Action Composition for 3D Humanscited by 176
  21. 2023Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perceptioncited by 167
  22. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 144
  23. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 139
  24. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 138
  25. 2023Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generationcited by 129
  26. 2024HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videoscited by 129
  27. 2023AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanismcited by 117
  28. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 114
  29. 2022AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensingcited by 110
  30. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character controlcited by 109
  31. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 104
  32. 2021Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimationcited by 101
  33. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 98
  34. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 94
  35. 2019Ego-Pose Estimation and Forecasting as Real-Time PD Controlcited by 87
  36. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 84
  37. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  38. 2019xR-EgoPose: Egocentric 3D Human Pose from an HMD Cameracited by 79

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learningcited by 3