Publications by authors named "Xingyi You"

Face recognition technology, despite its widespread use in various applications, still faces challenges related to occlusions, pose variations, and expression changes. Three-dimensional face recognition with depth information, particularly using point cloud-based networks, has shown effectiveness in overcoming these challenges. However, due to the limited extent of extensive 3D facial data and the non-rigid nature of facial structures, extracting distinct facial representations directly from point clouds remains challenging.

View Article and Find Full Text PDF
Article Synopsis
  • Growing concerns about personal data misuse from AI have led to the need for better privacy-protection methods, especially for facial data.
  • Existing facial privacy protection methods face issues like low visual quality and distortion, prompting the development of a new approach called Diffusion Models for Face Privacy Protection (DIFP).
  • DIFP uses a sophisticated face generator to create high-resolution photorealistic encrypted faces, allowing for effective identity recovery while maintaining natural facial characteristics, and has shown success in avoiding face recognition while enabling restoration of original faces when necessary.
View Article and Find Full Text PDF

In the past few years, 3D Morphing Model (3DMM)-based methods have achieved remarkable results in single-image 3D face reconstruction. However, high-fidelity 3D face texture generation has been successfully achieved with this method, which mostly uses the power of deep convolutional neural networks during the parameter fitting process, which leads to an increase in the number of network layers and computational burden of the network model and reduces the computational speed. Currently, existing methods increase computational speed by using lightweight networks for parameter fitting, but at the expense of reconstruction accuracy.

View Article and Find Full Text PDF

In a cyclic alternating O/A operation mode, phosphorus accumulating organisms (PAOs) can undertake phosphate removal and enrichment as the main process in wastewater treatment plants. The effects of the concentration of carbon sources during the aerobic stage on phosphate removal and enrichment performance of PAO biofilms, and the microbial population structure in the biofilms, were investigated. The results showed that the aerobic COD concentration decreased from 200 mg·L to 0 mg·L, the phosphorus uptake rate improved by 1.

View Article and Find Full Text PDF

A CANON reactor with fiber carrier was started up by seeding nitrification sludge and ANAMMOX sludge to study the operating characteristics of a fiber carrier. The results showed that total nitrogen removal load rose from 0.09 kg·(m·d) to 0.

View Article and Find Full Text PDF