Exploration de la connaissance de domaine et de la physique pour l'apprentissage de la translation d'image-à-image

Autor: Pizzati, Fabio <1993>

Publikováno v: Robotics [cs.RO]. Université Paris sciences et lettres; Università degli studi (Bologne, Italie), 2022. English. ⟨NNT : 2022UPSLM064⟩

Image-to-image (i2i) translation networks can generate fake images beneficial for many applications in augmented reality, computer graphics, and robotics. However, they require large-scale datasets and high contextual understanding to be trained corr

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36b87010d4d3444598b5ced602c16dd7