JMNet: A joint matting network for automatic human matting
Abstract We propose a novel end-to-end deep learning framework, the Joint Matting Network (JMNet), to automatically generate alpha mattes for human images. We utilize the intrinsic structures of the human body as seen in images by introducing a pose estimation module, which can provide both global s...
Bewaard in:
| Hoofdauteurs: | , , , |
|---|---|
| Formaat: | Artigo |
| Taal: | Inglês |
| Gepubliceerd in: |
Tsinghua University Press
2020-04-01
|
| Reeks: | Computational Visual Media |
| Onderwerpen: | |
| Online toegang: | https://doi.org/10.1007/s41095-020-0168-6 |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|