HADD: A hierarchy-aware disentangled diffusion framework with spatio-temporal denoising for 3D human pose estimation

Jinze Jiang, Zhongheng Jian, Hualing Zheng, Minsi Liang, Yuxing Shi, Liming Zhang · 2026

Read HADD: A hierarchy-aware disentangled diffusion framework with spatio-temporal denoising for 3D human pose estimation by Jinze Jiang, Zhongheng Jian, Hualing Zheng, Minsi Liang, Yuxing Shi, Liming Zhang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0359321.txt.

Description

Jiang and five co-authors published a 2026 PLOS ONE paper on guessing body poses in 3D from images. Their framework, HADD, is aware of body hierarchy and splits the pose into parts before cleaning the result. A denoising step works over space and time at once. Better pose tracking helps animation, sports analysis, and robots that need to follow human movement safely.

Catalog record

CREATORJinze Jiang, Zhongheng Jian, Hualing Zheng, Minsi Liang, Yuxing Shi, Liming Zhang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE157499
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0359321

Browse the full library · About the Tower of Babel