Articles producció científica> Enginyeria Informàtica i Matemàtiques

Promising Depth Map Prediction Method from a Single Image Based on Conditional Generative Adversarial Network

  • Datos identificativos

    Identificador: imarina:9380784
    Autores:
    Abdulwahab, SaddamRashwan, Hatem AMasoumian, ArminSharaf, NajwaPuig, Domenec
    Resumen:
    Pose estimation is typically performed through 3D images. In contrast, estimating the pose from a single RGB image is still a difficult task. RGB images do not only represent objects' shape, but also represent the intensity that is relative to the viewpoint, texture, and lighting condition. While the 3D pose estimation from depth images is considered a promising approach since the depth image only represents objects' shape. Thus, it is necessary to know what is the appropriate method that can be used for predicting the depth image from a 2D RGB image and then to use for getting the 3D pose estimation. In this paper, we propose a promising approach based on a deep learning model for depth estimation in order to improve the 3D pose estimation. The proposed model consists of two successive networks. The first network is an autoencoder network that maps from the RGB domain to the depth domain. The second network is a discriminator network that compares a real depth image to a generated depth image to support the first network to generate an accurate depth image. In this work, we do not use real depth images corresponding to the input color images. Our contribution is to use 3D CAD models corresponding to objects appearing in color images to render depth images from different viewpoints. These rendered images are then used as ground truth and to guide the autoencoder network to learn the mapping from the image domain to the depth domain. The proposed model outperforms state-of-the-art models on the publicly PASCAL 3D+ dataset.
  • Otros:

    Autor según el artículo: Abdulwahab, Saddam; Rashwan, Hatem A; Masoumian, Armin; Sharaf, Najwa; Puig, Domenec
    Departamento: Enginyeria Informàtica i Matemàtiques
    Autor/es de la URV: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / Abdulwahab, Saddam Abdulrhman Hamed / Masoumian, Armin / Puig Valls, Domènec Savi
    Palabras clave: Deep learning Depth prediction Image segmentation Image to image translatio Image to image translation Unet Unet plus Unet++
    Resumen: Pose estimation is typically performed through 3D images. In contrast, estimating the pose from a single RGB image is still a difficult task. RGB images do not only represent objects' shape, but also represent the intensity that is relative to the viewpoint, texture, and lighting condition. While the 3D pose estimation from depth images is considered a promising approach since the depth image only represents objects' shape. Thus, it is necessary to know what is the appropriate method that can be used for predicting the depth image from a 2D RGB image and then to use for getting the 3D pose estimation. In this paper, we propose a promising approach based on a deep learning model for depth estimation in order to improve the 3D pose estimation. The proposed model consists of two successive networks. The first network is an autoencoder network that maps from the RGB domain to the depth domain. The second network is a discriminator network that compares a real depth image to a generated depth image to support the first network to generate an accurate depth image. In this work, we do not use real depth images corresponding to the input color images. Our contribution is to use 3D CAD models corresponding to objects appearing in color images to render depth images from different viewpoints. These rendered images are then used as ground truth and to guide the autoencoder network to learn the mapping from the image domain to the depth domain. The proposed model outperforms state-of-the-art models on the publicly PASCAL 3D+ dataset.
    Áreas temáticas: Artificial intelligence Ciências agrárias i Comunicació i informació Engenharias iii Engenharias iv General o multidisciplinar Información y documentación Interdisciplinar Medicina ii
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    Direcció de correo del autor: domenec.puig@urv.cat saddam.abdulwahab@urv.cat armin.masoumian@estudiants.urv.cat armin.masoumian@estudiants.urv.cat hatem.abdellatif@urv.cat saddam.abdulwahab@urv.cat
    Identificador del autor: 0000-0002-0562-4205 0000-0001-5421-1637
    Fecha de alta del registro: 2024-09-21
    Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
    Referencia al articulo segun fuente origial: Frontiers In Artificial Intelligence And Applications. 339 392-401
    Referencia de l'ítem segons les normes APA: Abdulwahab, Saddam; Rashwan, Hatem A; Masoumian, Armin; Sharaf, Najwa; Puig, Domenec (2021). Promising Depth Map Prediction Method from a Single Image Based on Conditional Generative Adversarial Network. Amsterdam: IOS Press
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2021
    Tipo de publicación: Proceedings Paper
  • Palabras clave:

    Artificial Intelligence
    Deep learning
    Depth prediction
    Image segmentation
    Image to image translatio
    Image to image translation
    Unet
    Unet plus
    Unet++
    Artificial intelligence
    Ciências agrárias i
    Comunicació i informació
    Engenharias iii
    Engenharias iv
    General o multidisciplinar
    Información y documentación
    Interdisciplinar
    Medicina ii
  • Documentos:

  • Cerca a google

    Search to google scholar