In the era of artificial intelligence, face swapping technology has demonstrated its unique application value and broad prospects. Nevertheless, current research methods often struggle to achieve both rapidity and high quality while pursuing high-fidelity facial synthesis. In view of this, our study innovates on traditional models and integrates attention mechanisms, proposing a novel high-fidelity face swapping method:DFaker++. In terms of implementation, we first optimized and improved existing algorithms; secondly, by introducing an attention mechanism, the model can automatically focus on key facial areas in both source and target images, thereby more effectively preserving and blending facial features. Additionally, we employ the Huber loss function to guide model training, which shows better performance in cases with high noise or imperfect inputs. We propose a novel evaluation method for face swapping that merges objective metrics with subjective assessments, focusing on the quality of facial generation. Our experiments demonstrate that this approach outperforms existing models in both quality and efficiency, marking a significant step forward in facial synthesis technology.
In recent years, segmentation-based two-stage neural networks have emerged in the defect detection domain. Although these neural networks have shown great success in surface defect detection, they suffer from blurred edges, noise, and imbalanced data, which degrade the detection performance. In this study, we address these limitations by presenting a new two-stage defect detection framework. To solve the problem of defect detection with blurred edges, we propose leveraging multilevel representations during segmentation. Furthermore, we employ a joint loss function that combines the binary cross-entropy loss and Dice loss to reduce the influence of noise. Meanwhile, the joint loss function that contributes to our model is more robust for imbalanced data and is better for segmenting small-sized defects. To verify the performance of our proposed model, comprehensive experiments were conducted on two surface defect datasets: the Kolektor surface-defect dataset (KSDD) (http://www.vicos.si/Downloads/KolektorSDD) and the Deutsche Arbeitsgemeinschaft für Mustererkennung dataset (DAGM) (https://hci.iwr.uni-heidelberg.de/content/weakly-supervised-learning-industrial-optical-inspection). By performing more accurate segmentation of defects, our model shows superior results over the compared networks; it provided a 100% average precision on KSDD and 100% mean accuracy on DAGM, which demonstrates the effectiveness of our model.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.