Work

Resolving Facial Image Defects Through the Integration of Segmentation and Fusion Networks

Year: 2025

Type: article

Abstract: Generating images with dynamic expressions has become a key component of the social media industry. To enhance the realism, it is crucial to remove the potential distortion in the face image. Unfortunately, videos produced by PIrenderer often exhibit facial blur due to inadequate segmentation between foreground and background. In this paper, GrabCut and MODNet are used to post-process the videos generated by PIrenderer and then fuse them. Our proposed method can guarantee to reduce the influence of background on the face when generating dynamic expression videos. These post-processing steps optimize dynamic facial expression rendering, mitigate the face distortion problem, and ultimately produce more realistic video output.

Source: Applied and Computational Engineering

DOI: 10.54254/2755-2721/2025.bj25236

Authors: Zishuo Xia, Yin Ru, Yilei Yang, Kaiwen Xian

Institutions: Guangdong University of Foreign Studies, Gonzaga University, South China Normal University

Language: English

Topic: Face recognition and analysis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4413095639

FWCI:

Cites:

Cited by:

Related to: 10