A5031829023- Advanced Vision and Imaging
- Video Surveillance and Tracking Methods
- Medical Image Segmentation Techniques
- Ferroelectric and Negative Capacitance Devices
- Image Processing and 3D Reconstruction
- Industrial Vision Systems and Defect Detection
- Neural Networks and Reservoir Computing
- Advanced Measurement and Detection Methods
- Generative Adversarial Networks and Image Synthesis
- Advanced Memory and Neural Computing
- Handwritten Text Recognition Techniques
- Advanced Optical Sensing Technologies
- Optical measurement and interference techniques
- Computer Graphics and Visualization Techniques
- Image Enhancement Techniques
- Aesthetic Perception and Analysis
Zhejiang University
2024
Harbin Engineering University
2010-2023
3D human body reconstruction has been a challenge in the field of computer vision. Previous methods are often time-consuming and difficult to capture detailed appearance body. In this paper, we propose new method called \emph{Ultraman} for fast textured models from single image. Compared existing techniques, greatly improves speed accuracy while preserving high-quality texture details. We present set frameworks consisting three parts, geometric reconstruction, generation mapping. Firstly,...
The painting process of artists is inherently stepwise and varies significantly among different painters styles. Generating detailed, step-by-step processes essential for art education research, yet remains largely underexplored. Traditional stroke-based rendering methods break down images into sequences brushstrokes, they fall short replicating the authentic artists, with limitations confined to basic brushstroke modifications. Text-to-image models utilizing diffusion generate through...
The painting process of artists is inherently stepwise and varies significantly among different painters styles. Generating detailed, step-by-step processes essential for art education research, yet remains largely underexplored. Traditional stroke-based rendering methods break down images into sequences brushstrokes, they fall short replicating the authentic artists, with limitations confined to basic brushstroke modifications. Text-to-image models utilizing diffusion generate through...
In order to improve the quality of bionic robot vision tracking, new automatic tracking algorithm system is proposed in this paper. Based on completed hardware design and implementing scheme, scene noise removed by adaptive wiener filtering. Through improved sequential particle filter algorithm, dynamic target realized. The experiment result shows that still can lock accurately under condition outer contour changing partial occlusion existing.
To obtain better region extraction results of medical image, a new segmentation algorithm is proposed based on improved Adaboost algorithm. The seed pixel selected with background subtraction. neighborhood point judged. primary calibrated label, and then the range reduced through growing label maximal saliency. optimized taken as criterion to optimally combine scrappy when over. experiment result shows that accuracy robustness both meet actual application required.