mlsanityData to 7 Oct 2026

Panoptic Studio: A Massively Multiview System for Social Interaction Capture

arXiv 1612.03153 ↗First posted 9 Dec 2016cs.CVcited by 173

Not on the map. Why?

Abstract (arXiv)

We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the integration of perceptual analyses over a large variety of view points. We present a modularized system designed around this principle, consisting of integrated structural, hardware, and software innovations. The system takes, as input, 480 synchronized video streams of multiple people engaged in social activities, and produces, as output, the labeled time-varying 3D structure of anatomical landmarks on individuals in the space. Our algorithm is designed to fuse the "weak" perceptual processes in the large number of views by progressively generating skeletal proposals from low-level appearance cues, and a framework for temporal refinement is also presented by associating body parts to reconstructed dense 3D trajectory stream. Our system and method are the first in reconstructing full body motion of more than five people engaged in social interactions without using markers. We also empirically demonstrate the impact of the number of views in achieving this goal.

Key facts. Cited by 173 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 24; 2023: 21; 2024: 32; 2025: 26; 2026: 24.

173 papers.

Sort:

By area:

  1. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  2. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  3. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  4. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
  5. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  6. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  7. 2021Neural Articulated Radiance Fieldcited by 196
  8. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 168
  9. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  10. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  11. 2024Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wildcited by 109
  12. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
38 more
  1. 2025St4RTrack: Simultaneous 4D Reconstruction and Tracking in the Worldcited by 88
  2. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  3. 2023VR-NeRF: High-Fidelity Virtualized Walkable Spacescited by 86
  4. 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3Dcited by 69
  5. 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
  6. 2022NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactionscited by 67
  7. 2023A Comprehensive Review of Data-Driven Co-Speech Gesture Generationcited by 66
  8. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  9. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  10. 2021Playing for 3D Human Recoverycited by 63
  11. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  12. 2026SAM 3D Body: Robust Full-Body Human Mesh Recoverycited by 61
  13. 2024Learning the 3D Fauna of the Webcited by 58
  14. 2022MIME: Human-Aware 3D Scene Generationcited by 57
  15. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  16. 2023SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modelingcited by 54
  17. 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Meshcited by 51
  18. 20244D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotationscited by 51
  19. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  20. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  21. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  22. 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
  23. 2024ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesiscited by 41
  24. 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
  25. 2022Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesiscited by 40
  26. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 40
  27. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  28. 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
  29. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  30. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  31. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 32
  32. 2021Supervision by Registration and Triangulation for Landmark Detectioncited by 30
  33. 2021Weakly-Supervised Physically Unconstrained Gaze Estimationcited by 28
  34. 2021Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Camerascited by 26
  35. 2022Efficient Human Pose Estimation via 3D Event Point Cloudcited by 25
  36. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  37. 2025A Survey on Human Interaction Motion Generationcited by 25
  38. 2021Generalizable Human Pose Triangulationcited by 24

50 most cited of 173 All 173 (JSON)