Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


  • Fulltext

    Accepted author manuscript, 1.45 MB, PDF document

  • Zhuoran Zhou
  • Zhongyu Jiang
  • Wenhao Chai
  • Cheng-Yen Yang
  • Li, Lei
  • Jenq-Neng Hwang
Although 3D human pose estimation has gained impres-sive development in recent years, only a few works focus on infants, that have different bone lengths and also have limited data. Directly applying adult pose estimation mod-els typically achieves low performance in the infant domain and suffers from out-of-distribution issues. Moreover, the limitation of infant pose data collection also heavily con-strains the efficiency of learning-based models to lift 2D poses to 3D. To deal with the issues of small datasets, do-main adaptation and data augmentation are commonly used techniques. Following this paradigm, we take advantage of an optimization-based method that utilizes generative pri-ors to predict 3D infant keypoints from 2D keypoints with-out the need of large training data. We further apply a guided diffusion model to domain adapt 3D adult pose to infant pose to supplement small datasets. Besides, we also prove that our method, ZeDO-i, could attain efficient do-main adaptation, even if only a small number of data is given. Quantitatively, we claim that our model attains state-of-the-art MPJPE performance of 43.6 mm on the SyRIP dataset and 21.2 mm on the MINI-RGBD dataset.
Original languageEnglish
Title of host publication2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Number of pages9
Publication date2024
Publication statusPublished - 2024
EventWACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision - Waikola, Hawaii, United States
Duration: 4 Jan 20248 Jan 2024


ConferenceWACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision
LandUnited States
ByWaikola, Hawaii

ID: 378941805