15 citations · 20 across the 3 of their papers we have counts for
4 papers
ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation
Siyuan Bian, Jiefeng Li, Jiasheng Tang +1
Accurate human shape recovery from a monocular RGB image is a challenging task because humans come in different shapes and sizes and wear different clothes. In this paper, we propo…
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Jiefeng Li, Siyuan Bian, Qi Liu +3
With the progress of 3D human pose and shape estimation, state-of-the-art methods can either be robust to occlusions or obtain pixel-aligned accuracy in non-occlusion cases. Howeve…
HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery
Jiefeng Li, Siyuan Bian, Chao Xu +3
Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is…
Constructing Balance from Imbalance for Long-tailed Image Recognition
Yue Xu, Yong-Lu Li, Jiefeng Li +1
Long-tailed image recognition presents massive challenges to deep learning systems since the imbalance between majority (head) classes and minority (tail) classes severely skews th…