Please use this identifier to cite or link to this item:
Title: Delving into high-quality synthetic face occlusion segmentation datasets
Authors: Voo, Kenny Tze Rung
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Voo, K. T. R. (2022). Delving into high-quality synthetic face occlusion segmentation datasets. Final Year Project (FYP), Nanyang Technological University, Singapore.
Project: SCSE21-0206
Abstract: This paper performs comprehensive analysis on datasets for occlusion-aware face segmentation, a task that is crucial for many downstream applications. The collection and annotation of such datasets are time-consuming and labour-intensive. Although some efforts have been made in synthetic data generation, the naturalistic aspect of data remains less explored. In our study, we propose two occlusion generation techniques, Naturalistic Occlusion Generation (NatOcc), for producing high-quality naturalistic synthetic occluded faces; and Random Occlusion Generation (RandOcc), a more general synthetic occluded data generation method. We empirically show the effectiveness and robustness of both methods, even for unseen occlusions. To facilitate model evaluation, we present two high-resolution real-world occluded face datasets with fine-grained annotations, RealOcc and RealOcc-Wild, featuring both careful alignment preprocessing and an in-the-wild setting for robustness test. We further conduct a comprehensive analysis on a newly introduced segmentation benchmark, offering insights for future exploration.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
17.6 MBAdobe PDFView/Open

Page view(s)

Updated on May 20, 2022


Updated on May 20, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.