Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements (2306.07399v1)

Published 12 Jun 2023 in cs.CV

Abstract: This work presents 4DHumanOutfit, a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions. The dataset is designed to contain different actors wearing different outfits while performing different motions in each outfit. In this way, the dataset can be seen as a cube of data containing 4D motion sequences along 3 axes with identity, outfit and motion. This rich dataset has numerous potential applications for the processing and creation of digital humans, e.g. augmented reality, avatar creation and virtual try on. 4DHumanOutfit is released for research purposes at https://kinovis.inria.fr/4dhumanoutfit/. In addition to image data and 4D reconstructions, the dataset includes reference solutions for each axis. We present independent baselines along each axis that demonstrate the value of these reference solutions for evaluation tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. 4DViews 4DVManager software. Online https://www.4dviews.com/, 2023. Accessed on March 21st 2023.
  2. Kinovis, Inria 4D modeling multi cameras platform. Online http://kinovis.inria.fr/inria-platform, 2023. Accessed on March 21st 2023.
  3. Makehuman. Online http://makehuman.org/, 2023. Accessed on March 21st 2023.
  4. Mixamo. Online https://www.mixamo.com, 2023. Accessed on March 21st 2023.
  5. Video based reconstruction of 3d people models. In Conference on Computer Vision and Pattern Recognition, pages 8387–8397, 2018.
  6. SCAPE: shape completion and animation of people. ACM Transactions on Graphics, 24(3):408–416, 2005.
  7. D. J. Berndt and J. Clifford. Using dynamic time warping to find patterns in time series. In International Conference on Knowledge Discovery and Data Mining, page 359–370, 1994.
  8. Cloth3d: Clothed 3d humans. In European Conference on Computer Vision, pages 344–359, 2020.
  9. Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image. In European Conference on Computer Vision, pages 561–578, 2016.
  10. FAUST: Dataset and evaluation for 3D mesh registration. In Conference on Computer Vision and Pattern Recognition, pages 3794–3801, 2014.
  11. Dynamic FAUST: Registering human bodies in motion. In Conference on Computer Vision and Pattern Recognition, pages 5573–5582, 2017.
  12. HuMMan: Multi-modal 4d human dataset for versatile sensing and modeling. In European Conference on Computer Vision, pages 557–577, 2022.
  13. Inverse Elastic Cloth Design with Contact and Friction. Research report, Inria Grenoble, HAL id hal-01309617, 2016.
  14. Human4d: A human-centric multimodal dataset for motions and immersive media. IEEE Access, 8:176241–176262, 2020.
  15. Describing clothing by semantic attributes. In European Conference on Computer Vision, pages 609–623, 2012.
  16. Fashion meets computer vision: A survey. ACM Computing Surveys, 54(4):1–41, 2021.
  17. Performance capture from sparse multi-view video. ACM Transactions on Graphics, 27(3):#98,1–10, 2008.
  18. Fw-gan: Flow-navigated warping gan for video virtual try-on. In International Conference on Computer Vision, pages 1161–1170, 2019.
  19. Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time. Transactions on Pattern Analysis and Machine Intelligence, 45(6):7157–7173, 2023.
  20. Probabilistic character motion synthesis using a hierarchical deep latent variable model. Computer Graphics Forum, 39(8):225–239, 2020.
  21. Drape: Dressing any person. Transactions on Graphics, 31(4):1–10, 2012.
  22. Viton: An image-based virtual try-on network. In Conference on Computer Vision and Pattern Recognition, pages 7543–7552, 2018.
  23. A statistical model of human pose and body shape. Computer Graphics Forum, 2(28):337–346, 2009.
  24. Learning to train with synthetic humans. In German Conference on Pattern Recognition, pages 609–623, 2019.
  25. B. Huang. Mvsmplfitting. https://github.com/boycehbz/MvSMPLfitting.
  26. Human3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. Transactions on Pattern Analysis and Machine Intelligence, 36(7):1325–1339, 2013.
  27. Fashionpedia: Ontology, segmentation, and an attribute localization dataset. In European Conference on Computer Vision, pages 316–332, 2020.
  28. Bcnet: Learning body and cloth shape from a single image. In European Conference on Computer Vision, pages 18–35, 2020.
  29. H4D: human 4d modeling by learning neural compositional representation. In Conference on Computer Vision and Pattern Recognition, pages 19355–19365, 2022.
  30. Panoptic studio: A massively multiview system for social interaction capture. Transactions on Pattern Analysis and Machine Intelligence, 41(1):190–204, 2017.
  31. M. Korosteleva and S.-H. Lee. Generating datasets of 3d garments with sewing patterns. In Neural Information Processing Systems Track on Datasets and Benchmarks, 2021.
  32. Multi-view dynamic shape refinement using local temporal integration. In IEEE,International Conference on Computer Vision, pages 3113–3122, 2017.
  33. Learning a model of facial shape and expression from 4D scans. Transactions on Graphics, 36(6):194:1–194:17, 2017.
  34. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In Conference on Computer Vision and Pattern Recognition, pages 1096–1104, 2016.
  35. SMPL: a skinned multi-person linear model. Transactions on Graphics, 34(6):1–16, 2015.
  36. Learning to dress 3d people in generative clothing. In Conference on Computer Vision and Pattern Recognition, pages 6468–6477, 2020.
  37. Learning cloth dynamics: 3d+ texture garment reconstruction benchmark. In Conference on Neural Information Processing Systems Competition and Demos, pages 57–76, 2020.
  38. Amass: Archive of motion capture as surface shapes. In International Conference on Computer Vision, pages 5442–5451, 2019.
  39. Correspondence-free online human motion retargeting. arXiv 2302.00556, 2023.
  40. A structured latent space for human body motion generation. In Conference on 3D Vision, pages 557–566, 2022.
  41. Monocular 3D human pose estimation in the wild using improved cnn supervision. In Conference on 3D Vision, pages 506–516, 2017.
  42. Single-shot multi-person 3D pose estimation from monocular RGB. In Conference on 3D Vision, pages 120–130, 2018.
  43. Agora: Avatars in geography optimized for regression analysis. In Conference on Computer Vision and Pattern Recognition, pages 13468–13478, 2021.
  44. Clothcap: Seamless 4d clothing capture and retargeting. Transactions on Graphics, 36(4), 2017.
  45. Dyna: A model of dynamic human shape in motion. Transactions on Graphics, 34(4):120:1–120:14, 2015.
  46. 3Dpeople: Modeling the geometry of dressed humans. In International Conference on Computer Vision, pages 2242–2251, 2019.
  47. Learning multi-human optical flow. International Journal of Computer Vision, 128:873–890, 2020.
  48. J. Regateiro and E. Boyer. Temporal shape transfer network for 3d human motion. In Conference on 3D Vision, pages 424–432, 2022.
  49. The CAESAR project: A 3-D surface anthropometry survey. In Conference on 3D Digital Imaging and Modeling, pages 180–186, 1999.
  50. Embodied hands: Modeling and capturing hands and bodies together. Transactions on Graphics, 36(6):245:1–245:17, 2017.
  51. Snug: Self-supervised neural dynamic garments. In Conference on Computer Vision and Pattern Recognition, pages 8130–8140, 2022.
  52. Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. International Journal of Computer Vision, 87(1-2):4, 2010.
  53. Hand keypoint detection in single images using multiview bootstrapping. Conference on Computer Vision and Pattern Recognition, pages 4645–4653, 2017.
  54. J. Starck and A. Hilton. Surface capture for performance-based animation. Computer Graphics and Applications, 27(3):21–31, 2007.
  55. Sizer: A dataset and model for parsing 3d clothing and learning size sensitive 3d clothing. In European Conference on Computer Vision, pages 1–18, 2020.
  56. Total capture: 3d human pose estimation fusing video and inertial sensors. In British Machine Vision Conference, pages 1–13, 2017.
  57. Learning from synthetic humans. In Conference on Computer Vision and Pattern Recognition, pages 109–117, 2017.
  58. Contact-aware retargeting of skinned motion. In International Conference on Computer Vision, pages 9700–9709, 2021.
  59. Dynamic shape capture using multi-view photometric stereo. Transactions on Graphics, 28(5):174:1–12, 2009.
  60. Neural pose transfer by spatially adaptive instance normalization. In Conference on Computer Vision and Pattern Recognition, pages 5831–5839, 2020.
  61. Dance in the wild: Monocular human animation with neural dynamic appearance synthesis. In International Conference on 3D Vision, pages 268–277, 2021.
  62. Monoperfcap: Human performance capture from monocular video. Transactions on Graphics, 37(2):1–15, 2018.
  63. Parsing clothing in fashion photographs. In Conference on Computer Vision and Pattern Recognition, pages 3570–3577, 2012.
  64. Estimation of human body shape in motion with wide clothing. In European Conference on Computer Vision, pages 439–454, 2016.
  65. Hi4d: 4d instance segmentation of close human interaction. In Computer Vision and Pattern Recognition, pages 17016–17027, 2023.
  66. Humbi: A large multiview dataset of human body expressions and benchmark challenge. Transactions on Pattern Analysis and Machine Intelligence, 45(1):623–640, 2021.
  67. Detailed, accurate, human shape estimation from clothed 3d scan sequences. In Conference on Computer Vision and Pattern Recognition, pages 5484–5493, 2017.
  68. Deephuman: 3d human reconstruction from a single image. In International Conference on Computer Vision, pages 7739–7749, 2019.
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now