XINYANG LI

Dr. XINYANG LI

Cheongju University, Cheongju-si, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2025 in Sensors
Verified
Journal Article
Open access
PDF file
YTYIHUAN TIAN
YIHUAN TIAN
XLXINYANG LI
XINYANG LI
ZCZULING CHENG
ZULING CHENG
Yang HuangYang Huang
Yang Huang
TYTao Yu
Tao Yu
The rise of virtual production has created an urgent need for both efficient and high-fidelity 3D face generation schemes for cinema and immersive media, but existing methods are often limited by lighting–geometry coupling, multi-view dependency, and insufficient artistic quality. To address this, this study proposes a cross-modal 3D face generation framework based on single-view semantic masks. It utilizes Swin Transformer for multi-level feature extraction and combines with NeRF for illumination decoupled rendering. We utilize physical rendering equations to explicitly separate surface reflectance from ambient lighting to achieve robust adaptation to complex lighting variations. In addition, to address geometric errors across illumination scenes, we construct geometric a priori constraint networks by mapping 2D facial features to 3D parameter space as regular terms with the help of semantic masks. On the CelebAMask-HQ dataset, this method achieves a leading score of SSIM = 0.892 (37.6% improvement from baseline) with FID = 40.6. The generated faces excel in symmetry and detail fidelity with realism and aesthetic scores of 8/10 and 7/10, respectively, in a perceptual evaluation with 1000 viewers. By combining physical-level illumination decoupling with semantic geometry a priori, this paper establishes a quantifiable feedback mechanism between objective metrics and human aesthetic evaluation, providing a new paradigm for aesthetic quality assessment of AI-generated content.

17 August 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
SLShiwen Lai
Shiwen Lai
YTYIHUAN TIAN
YIHUAN TIAN
XLXINYANG LI
XINYANG LI
The Ganjiang River–Poyang Lake Basin is a typical river–lake composite water-system region and a major concentration area of intangible cultural heritage (ICH) in Jiangxi Province. However, officially listed ICH does not simply represent the natural distribution of cultural practices but reflects the combined effects of historical accumulation, environmental contexts, and institutional recognition. Based on 616 national- and provincial-level ICH items, this study employs the nearest neighbor index, kernel density analysis, Lorenz curve, standard deviational ellipse, and Geodetector to examine spatial patterns and associated factors. The results reveal significant spatial clustering (NNI = 0.31, Z = −39.16), characterized by riverine concentration, lakeside distribution, and polycentric development. Traditional craftsmanship and folk customs cluster around Poyang Lake, while traditional drama, folk literature, and quyi extend along the Ganjiang River. Distance to major water systems (q = 0.821), policy support (q = 0.813), and inheritors (q = 0.806) show the highest explanatory power. The findings reveal a spatial process of lake-area accumulation, river-channel diffusion, and nodal support.