mlsanityData to 14 Oct 2026

HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge

arXiv 2110.00119 ↗First posted 30 Sep 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of five primary body signals including gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cameras are used to capture 772 distinctive subjects across gender, ethnicity, age, and style. With the multiview image streams, we reconstruct high fidelity body expressions using 3D mesh models, which allows representing view-specific appearance. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complementary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3.6M, and Panoptic Studio datasets. Based on HUMBI, we formulate a new benchmark challenge of a pose-guided appearance rendering task that aims to substantially extend photorealism in modeling diverse human expressions in 3D, which is the key enabling factor of authentic social tele-presence. HUMBI is publicly available at http://humbi-data.net

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 63 of its 128 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

63 of 128 references.

References · 63

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  6. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  7. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  8. 2019YOLACT: Real-time Instance Segmentationcited by 443
  9. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  10. 2017Learning from Synthetic Humanscited by 359
  11. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  12. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
38 more
  1. 2017Pose Guided Person Image Generationcited by 251
  2. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  3. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  4. 2018Video Based Reconstruction of 3D People Modelscited by 238
  5. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  6. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  7. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  8. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  9. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  10. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  11. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  12. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  13. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  14. 2018Deep Appearance Models for Face Renderingcited by 164
  15. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  16. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  17. 2015Appearance-Based Gaze Estimation in the Wildcited by 153
  18. 2020TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Stylecited by 149
  19. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  20. 2020ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variationcited by 141
  21. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  22. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  23. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  24. 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 120
  25. 2019CLOTH3D: Clothed 3D Humanscited by 116
  26. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 115
  27. 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
  28. 2019Dense Intrinsic Appearance Flow for Human Pose Transfercited by 104
  29. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 103
  30. 2020Deep Image Spatial Transformation for Person Image Generationcited by 100
  31. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  32. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  33. 2019Learning-Based Animation of Clothing for Virtual Try-Oncited by 89
  34. 2020SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothingcited by 87
  35. 2017Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensorcited by 84
  36. 2019360-Degree Textures of People in Clothing from a Single Imagecited by 75
  37. 2018Photo Wake-Up: 3D Character Animation from a Single Photocited by 60
  38. 2021Neural Re-Rendering of Humans from a Single Imagecited by 59

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 5; 2024: 7; 2025: 1; 2026: 3.

17 papers.

Sort:

By area:

  1. 2023A Dataset of Relighted 3D Interacting Handscited by 35
  2. 2024Synergistic Global-space Camera and Human Reconstruction from Videoscited by 17
  3. 20234DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacementscited by 12
  4. 2024Reconstructing Close Human Interactions from Multiple Viewscited by 7
  5. 2024UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cuescited by 6
  6. 2023FSVVD: A Dataset of Full Scene Volumetric Videocited by 5
  7. 2023A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimizationcited by 5
  8. 2025Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interactioncited by 5
  9. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  10. 2024WildAvatar: Learning In-the-wild 3D Avatars from the Webcited by 3
  11. 2021Putting 3D Spatially Sparse Networks on a Dietcited by 2
  12. 2024Vid3D: Synthesis of Dynamic 3D Scenes using 2D Video Diffusioncited by 1
5 more
  1. 2024Are Pose Estimators Ready for the Open World? STAGE: A GenAI Toolkit for Auditing 3D Human Pose Estimatorscited by 1
  2. 2026ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptationcited by 1
  3. 2026VolHuMe: a High-Resolution Large Scale Dataset of Volumetric Human Meshescited by 1
  4. 2026FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Imagecited by 1
  5. 2024A New People-Object Interaction Dataset and NVS Benchmarkscited by 0