A5101956350- Computer Graphics and Visualization Techniques
- 3D Shape Modeling and Analysis
- Gold and Silver Nanoparticles Synthesis and Applications
- Advanced Image and Video Retrieval Techniques
- Nanoplatforms for cancer theranostics
- Image Processing and 3D Reconstruction
- Nanoparticle-Based Drug Delivery
- Evacuation and Crowd Dynamics
- Image and Signal Denoising Methods
- Cryptography and Data Security
- Industrial Technology and Control Systems
- Medical Image Segmentation Techniques
- Traffic control and management
- Railway Systems and Energy Efficiency
- Advanced Vision and Imaging
- Remote Sensing and Land Use
- Advanced Algorithms and Applications
- Transportation Planning and Optimization
- Educational Technology and Assessment
- Chaos-based Image/Signal Encryption
- Anomaly Detection Techniques and Applications
- Higher Education and Teaching Methods
- Advanced Image Fusion Techniques
- Advanced Computational Techniques and Applications
- Spectroscopy Techniques in Biomedical and Chemical Research
Southeast University
2024
Hangzhou Dianzi University
2020-2024
Zhejiang University
2021-2024
Tencent (China)
2024
Nankai University
2023
Shanghai Dianji University
2021
State Key Laboratory of Oncogene and Related Genes
2020
Shanghai Jiao Tong University
2020
Beijing Union University
2018
Jiangsu Yonggang Group (China)
2010
Recent advancements in 2D diffusion models allow appearance generation on untextured raw meshes. These methods create RGB textures by distilling a model, which often contains unwanted baked-in shading effects and results unrealistic rendering the downstream applications. Generating Physically Based Rendering (PBR) materials instead of just would be promising solution. However, directly PBR material parameters from still suffers incorrect decomposition, such as albedo. We introduce DreamMat ,...
Style-guided texture generation aims to generate a that is harmonious with both the style of reference image and geometry input mesh, given 3D mesh its text description. Although diffusion-based methods, such as distillation sampling, have numerous promising applications in stylized games films, it requires addressing two challenges: 1) decouple content completely from for models, 2) align generated color tone, image, prompt. To this end, we introduce StyleTex, an innovative...
Abstract Realistic crowd simulation has been pursued for decades, but it still necessitates tedious human labour and a lot of trial error. The majority currently used modelling is either empirical (model‐based) or data‐driven (model‐free). Model‐based methods cannot fit observed data precisely, whereas model‐free are limited by the availability/quality uninterpretable. In this paper, we aim at taking advantage both model‐based approaches. order to accomplish this, propose new framework built...
With the growing prominence of outsourcing services and increasing user concerns about security, existing encryption image retrieval schemes suffer from several limitations, such as low efficiency, poor accuracy, inadequate scalability. Therefore, we propose an encrypted scheme by dividing clustering subspace with vertical parallels to construct indexes. Concretely, data owners upload preprocessed classified datasets a fully trusted auxiliary server. Subsequently, server clusters images...
Abstract In this paper, an intelligent early warning scheme for rail transit line trip based on PSCADA system is proposed. The takes into account the defects of low prediction accuracy and real-time caused by lack power data in traditional method. At same time, a large number generated long-term application process are ignored field transit[1]. Based situation, set constructed combining historical collected lightning weather methods. On basis, lightgbm machine learning algorithm used to...