H-GAN: the power of GANs in your Hands
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/114586
Título: | H-GAN: the power of GANs in your Hands |
---|---|
Autor/es: | Oprea, Sergiu | Karvounas, Giorgos | Martínez González, Pablo | Kyriazis, Nikolaos | Orts-Escolano, Sergio | Oikonomidis, Iason | Garcia-Garcia, Alberto | Tsoli, Aggeliki | Garcia-Rodriguez, Jose | Argyros, Antonis |
Titular/es del derecho: | Universidad de Alicante | Institute of Computer Science, FORTH, Greece |
Grupo/s de investigación o GITE: | 3D Perception Lab |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Tecnología Informática y Computación |
Palabras clave: | Synthetic-to-real | Generative adversarial networks | Cycle-consistency | Perceptual discriminator |
Área/s de conocimiento: | Arquitectura y Tecnología de Computadores |
Fecha de creación: | 2020 |
Fecha de publicación: | 2021 |
Resumen: | We present HandGAN (H-GAN), a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators. It is designed to translate synthetic images of hands to the real domain. Synthetic hands provide complete ground-truth annotations, yet they are not representative of the target distribution of real-world data. We strive to provide the perfect blend of a realistic hand appearance with synthetic annotations. Relying on image-to-image translation, we improve the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images of hands. H-GAN tackles not only the cross-domain tone mapping but also structural differences in localized areas such as shading discontinuities. Results are evaluated on a qualitative and quantitative basis improving previous works. Furthermore, we relied on the hand classification task to claim our generated hands are statistically similar to the real domain of hand. |
Patrocinador/es: | Spanish Government PID2019-104818RB-I00 grant for the MoDeaAS project, supported with Feder funds. This work has also been supported by two Spanish national grants for PhD studies, FPU17/00166, and ACIF/2018/197 respectively. |
URI: | http://hdl.handle.net/10045/114586 |
Idioma: | eng |
Tipo: | software |
Derechos: | © Universitat d'Alacant / Universidad de Alicante. Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) |
Revisión científica: | no |
Versión del editor: | https://arxiv.org/abs/2103.15017 |
Aparece en las colecciones: | Registro de Programas de Ordenador y Bases de Datos |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
HGAN.pdf | Repositorio H-GAN: the power of GANs in your Hands | 581,63 kB | Adobe PDF | Abrir Vista previa |
Este ítem está licenciado bajo Licencia Creative Commons