Journal
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
Volume 95, Issue -, Pages -Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jvcir.2023.103881
Keywords
3D human modeling; Deep Neural Networks; Body part attentions; Kinematic chain-based decoder
Ask authors/readers for more resources
We propose a part-attentive kinematic regressor for 3D human modeling, which predicts body part attentions and estimates parameters of the 3D human model via attentive features. This method has the ability to yield natural shapes and poses even with severe occlusions, as demonstrated by experimental results on benchmark datasets.
As the demand for realistic representation and its applications increases rapidly, 3D human modeling via a single RGB image has become the essential technique. Owing to the great success of deep neural networks, various learning-based approaches have been introduced for this task. However, partial occlusions still give the difficulty to accurately estimate the 3D human model. In this letter, we propose the part-attentive kinematic regressor for 3D human modeling. The key idea of the proposed method is to predict body part attentions based on each body center position and estimate parameters of the 3D human model via corresponding attentive features through the kinematic chain-based decoder in a one-stage fashion. One important advantage is that the proposed method has a good ability to yield natural shapes and poses even with severe occlusions. Experimental results on benchmark datasets show that the proposed method is effective for 3D human modeling under complicated real-world environments. The code and model are publicly available at: https://github.com/DCVL-3D/PKCN_release
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available