Видалення тіней із зображення за допомогою генеративних змагальних мереж та навчання без учителя
Loading...
Date
2020
Authors
Андронік, Владислав
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This material presents the solution for shadow removal task using generative
adversarial networks. Our approach is trained in unsupervised fashion which means it
does not depend on time-consuming data collection and annotation. This together
with training in a single end-to-end framework significantly raises its practical
relevance.
Taking the existing method for unsupervised image transfer between different
domains we researched its applicability to the shadow removal problem. By
exploiting attention modules and multi context feature aggregation using dilated
convolutions our method gives significant results compared to existing solutions in
the field.
Description
Keywords
generative adversarial networks, unsupervised learning, shadow removal, shadow generation, attention module, dilated convolutions, курсова робота