mlsanityData to 14 Oct 2026

Reconstructing Three-Dimensional Models of Interacting Humans

arXiv 2308.01854 ↗First posted 3 Aug 2023cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Understanding 3d human interactions is fundamental for fine-grained scene analysis and behavioural modeling. However, most of the existing models predict incorrect, lifeless 3d estimates, that miss the subtle human contact aspects--the essence of the event--and are of little use for detailed behavioral understanding. This paper addresses such issues with several contributions: (1) we introduce models for interaction signature estimation (ISP) encompassing contact detection, segmentation, and 3d contact signature prediction; (2) we show how such components can be leveraged to ensure contact consistency during 3d reconstruction; (3) we construct several large datasets for learning and evaluating 3d contact prediction and reconstruction methods; specifically, we introduce CHI3D, a lab-based accurate 3d motion capture dataset with 631 sequences containing 2,525 contact events, 728,664 ground truth 3d poses, as well as FlickrCI3D, a dataset of 11,216 images, with 14,081 processed pairs of people, and 81,233 facet-level surface correspondences. Finally, (4) we propose methodology for recovering the ground-truth pose and shape of interacting people in a controlled setup and (5) annotate all 3d interaction motions in CHI3D with textual descriptions. Motion data in multiple formats (GHUM and SMPLX parameters, Human3.6m 3d joints) is made available for research purposes at urlhttps://ci3d.imar.ro, together with an evaluation server and a public benchmark.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 32 of its 69 references that are in the map. First posted on arXiv 3 Aug 2023.

Builds on

32 of 69 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  7. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  8. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  11. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  12. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
20 more
  1. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  2. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  3. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  4. 2019ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imagingcited by 147
  5. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  6. 2015Capturing Hands in Action using Discriminative Salient Points and Physics Simulationcited by 115
  7. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  8. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  9. 2021On Self-Contact and Human Posecited by 89
  10. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  11. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  12. 2021Multi-Person Extreme Motion Predictioncited by 75
  13. 2021Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Cameracited by 70
  14. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  15. 2020Learning Complex 3D Human Self-Contactcited by 40
  16. 2019Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Informationcited by 35
  17. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  18. 2018Learning to Refine Human Pose Estimationcited by 19
  19. 2020PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimationcited by 15
  20. 2017A Comparison of Directional Distances for Hand Pose Estimationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 3.

14 papers.

Sort:

By area:

  1. 2025PromptHMR: Promptable Human Mesh Recoverycited by 76
  2. 2024Monocular Occupancy Prediction for Scalable Indoor Scenescited by 31
  3. 2025The Quest for Generalizable Motion Generation: Data, Model, and Evaluationcited by 22
  4. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 19
  5. 2025DanceTogether! Identity-Preserving Multi-Person Interactive Video Generationcited by 13
  6. 2024Synergy and Synchrony in Couple Dancescited by 9
  7. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  8. 20253D Human Interaction Generation: A Surveycited by 7
  9. 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoningcited by 4
  10. 2025CoMPAS3D: A Dataset and Benchmark for Interactive Motioncited by 2
  11. 2025HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenariocited by 1
  12. 2026JRDB-Pose3D: A Multi-person 3D Human Pose and Shape Estimation Dataset for Roboticscited by 1
2 more
  1. 2026MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editingcited by 1
  2. 2026InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recoverycited by 0