Single Source One Shot Reenactment using Weighted Motion from Paired Feature Points

Soumya Tripathy, Juho Kannala, Esa Rahtu

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

5 Sitaatiot (Scopus)

Abstrakti

Image reenactment is a task where the target object in the source image imitates the motion represented in the driving image. One of the most common reenactment tasks is face image animation. The major challenge in the current face reenactment approaches is to distinguish between facial motion and identity. For this reason, the previous models struggle to produce high-quality animations if the driving and source identities are different (cross-person reenactment). We propose a new (face) reenactment model that learns shape-independent motion features in a self-supervised setup. The motion is represented using a set of paired feature points extracted from the source and driving images simultaneously. The model is generalised to multiple reenactment tasks including faces and non-face objects using only a single source image. The extensive experiments show that the model faithfully transfers the driving motion to the source while retaining the source identity intact.

AlkuperäiskieliEnglanti
OtsikkoProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
KustantajaIEEE
Sivut2121-2130
Sivumäärä10
ISBN (elektroninen)978-1-6654-0915-5
DOI - pysyväislinkit
TilaJulkaistu - 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Winter Conference on Applications of Computer Vision - Waikoloa, Yhdysvallat
Kesto: 4 tammik. 20228 tammik. 2022
Konferenssinumero: 22

Julkaisusarja

NimiIEEE Winter Conference on Applications of Computer Vision
ISSN (elektroninen)2642-9381

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
LyhennettäWACV
Maa/AlueYhdysvallat
KaupunkiWaikoloa
Ajanjakso04/01/202208/01/2022

Sormenjälki

Sukella tutkimusaiheisiin 'Single Source One Shot Reenactment using Weighted Motion from Paired Feature Points'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä