A5030824965- 3D Shape Modeling and Analysis
- Generative Adversarial Networks and Image Synthesis
- Computer Graphics and Visualization Techniques
- Color perception and design
- Textile materials and evaluations
- Scheduling and Optimization Algorithms
- Assembly Line Balancing Optimization
- Human Pose and Action Recognition
- Environmental Impact and Sustainability
- Advanced Manufacturing and Logistics Optimization
- Consumer Retail Behavior Studies
- Human Motion and Animation
- Face recognition and analysis
- Video Surveillance and Tracking Methods
- Manufacturing Process and Optimization
- Fashion and Cultural Textiles
- Optimization and Packing Problems
- Gait Recognition and Analysis
- Recommender Systems and Techniques
- Ergonomics and Musculoskeletal Disorders
- Advanced Neural Network Applications
- Hand Gesture Recognition Systems
- Aesthetic Perception and Analysis
- Consumer Perception and Purchasing Behavior
- Industrial Vision Systems and Defect Detection
Hong Kong Polytechnic University
2016-2025
National Sun Yat-sen University
2025
Beijing Academy of Artificial Intelligence
2021-2024
Shenzhen Polytechnic
2017-2020
Chinese University of Hong Kong
2002-2005
This paper reports on the development of \textbf{a novel style guided diffusion model (SGDiff)} which overcomes certain weaknesses inherent in existing models for image synthesis. The proposed SGDiff combines modality with a pretrained text-to-image to facilitate creative fashion It addresses limitations by incorporating supplementary guidance, substantially reducing training costs, and overcoming difficulties controlling synthesized styles text-only inputs. also introduces new dataset --...
Being essential in animation creation, colorizing anime line drawings is usually a tedious and time-consuming manual task. Reference-based drawing colorization provides an intuitive way to automatically colorize target using reference images. The prevailing approaches are based on generative adversarial networks (GANs), yet these methods still cannot generate high-quality results comparable manually-colored ones. In this paper, new AnimeDiffusion approach proposed via hybrid diffusions for...
Abstract Personalized 3D human avatars have aroused a great deal of interest because it is attractive to most people, particularly generation Z, the digital twins in their own appearance live, work, interact, and shop metaverse. Nevertheless, personalized are rarely used practice computational cost hardware restrictions creation process. This has resulted diverse topologies being on different platforms/systems for various applications, which further hinders utilization avatars. paper reports...
Rapid advancements in generative models, including adversarial networks (GANs) and diffusion have made possible of automated image editing through the use text descriptions, semantic segmentation, and/or reference style images. Nevertheless, terms fashion editing, it often requires more flexible, typically iterative, modifications to content that existing methods struggle achieve. This paper proposes a new model called Content Decoupled Enhanced GAN (CoDE-GAN), which is formulated trained...
The effective detection of repeated patterns from inputs unknown fronto-parallel images is an important computer vision task that supports many real-world applications, such as image retrieval, synthesis, and texture analysis. A pattern defined the smallest unit capable tiling entire image, representing its primary structural visual information. In this paper, a hybrid method proposed, overcoming drawbacks both traditional existing deep learning-based approaches. new leverages features...
This paper reviews published research in the field of computer-aided colorization technology. We argue that within this context, task can be considered to originate from computer graphics, advance by introducing vision, and progress towards fusion vision graphics. Hence, we propose a specific taxonomy organize work chronologically. extend existing reconstruction-based evaluation techniques on basis aesthetic assessment should introduced ensure computer- colored images closely satisfy human...
ABSTRACT Considering the pivotal role of creativity across various eras and rapid integration Artificial Intelligence (AI) in both creative processes education, this study introduces provides validity evidence for AI‐assisted Creativity Questionnaire (AICQ). This new 16‐item instrument aims to quantify human potential endeavors. Initially, a diverse cohort 322 university students Taiwan completed AICQ from November December 2023. Through exploratory factor analysis (EFA) responses sample,...