Does the input image spatial resolution generate different synthetic images? A Comparative Study of Facial Expression Synthesis Performance

Author(s)

Testa, Rafael Luiz ; Machado-Lima, Ariane ; Nunes, Fatima L. S.

• Document type: Journal article
• Source: 2023 36TH CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, SIBGRAPI 2023; v. N/A, p. 6-pg., 2023-01-01.

Abstract

Facial expression synthesis has gained significant attention in the image synthesis field. Generative Adversarial Network (GAN) models have recently gained popularity due to the high-quality synthetic images they produce. However, these models require complex network architectures that can take days to train, even with high-performance Graphics Processing Units (GPUs). Many efforts have been made to accelerate and compress such models, but little attention has been paid to the resolution of the images. This study aims to assess the impact of input/output spatial resolution on the resources needed for training a facial expression synthesis model, as well as on the quality of the results. Our results indicate that the produced images and videos had similar quality results measured through objective measures for the spatial resolution of 128 x 128, 256 x 256, and 480 x 480. Furthermore, we found that lower-resolution images could significantly reduce the time required to generate new facial expressions without compromising quality, as measured by objective measures. (AU)

• FAPESP's process: 14/50889-7 - National Institute of Science and Technology Medicine Assisted by Scientific Computing (INCT-MACC)
• Grantee: José Eduardo Krieger
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 20/01992-0 - Computer aid system for the diagnosis of psychiatric disorders based on facial anthropometric measurements
• Grantee: Ariane Machado Lima
• Support Opportunities: Research Grants - eScience and Data Science Program - Regular Program Grants