Buscar en Google Scholar
Título: Flash image enhancement via ratio-log image translation to ambient images
Asesor(es): Cayllahua Cahuina, Edward Jorge Yuri
Campo OCDE: http://purl.org/pe-repo/ocde/ford#1.02.01
Fecha de publicación: 2021
Institución: Universidad Católica San Pablo
Resumen: To illuminate low-light scenarios in photography, photographers usually use the camera flash, this produces flash images. Nevertheless, this external light may produce non-uniform illumination and unnatural color of objects, especially in low-light conditions. On the other hand, in an ambient image, an image captured with the available light in the ambient, the illumination is evenly distributed. We therefore consider ambient images as the enhanced version of flash images. Thus, with a fully convolutional network, and a flash image as input, we first estimate the ratio-log image. Then, our model produces the ambient image by using the estimated ratio-log image and ash image. Hence, high-quality information is recovered with the flash image. Our model generates suitable natural and uniform illumination on the FAID dataset with SSIM = 0:662, and PSNR = 15:77, and achieves better performance than state-of-the-art methods. We also analyze the components of our model and how they affect the overall performance. Finally, we introduce a metric to measure the similarity of naturalness of illumination between target and predicted images.
Disciplina académico-profesional: Ciencia de la Computación
Institución que otorga el grado o título: Universidad Católica San Pablo. Departamento de Ciencia de la Computación
Grado o título: Maestro en Ciencia de la Computación
Jurado: José Eduardo Ochoa Luna; Guillermo Cámara Chávez; Javier Montoya Zegarra; Edwin Jonathan Escobedo Cárdenas
Fecha de registro: 1-jul-2021



Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons Creative Commons