Abstract | ||
---|---|---|
Despite some successes have been made in face swapping research, face swapping is still not robust and real-time enough. In this paper, a robust and real-time method for face swapping based on face segmentation and CANDIDE-3 is proposed. We implement our method through four steps: face detection, face alignment, modelling and swapping. We test our method on three publicly available datasets and some videos, and results show that our method can effectively improve the robust and real-time performance of face swapping. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-97310-4_38 | PRICAI 2018: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II |
Keywords | Field | DocType |
Face swapping, Face segmentation, CANDIDE-3 model | Swap (computer programming),Pattern recognition,Segmentation,Computer science,Artificial intelligence,Face detection | Conference |
Volume | ISSN | Citations |
11013 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haosen Wang | 1 | 0 | 0.34 |
Dongliang Xie | 2 | 251 | 21.85 |
Lu Wei | 3 | 0 | 0.34 |