About me

👋 Hello, welcome to my homepage!

My name is Zhiwei Wang(王志伟), and I am currently a Ph.D. candidate at Zhejiang University of Technology. My research primarily focuses on multi-modal image fusion and perception, as well as their efficient deployment on embedded systems for real-world applications.

🔥 News

2025.10: 😄 Awarded Outstanding Graduate Student Cadre

2025.09: 🎉🎉🎉 DiFusionSeg: Diffusion-Driven Semantic Segmentation with Multi-Modal Image Fusion for Enhanced Perception — Accepted by Knowledge-Based Systems

2024.10: 🎉 U-Net Semantic Segmentation-Based Calorific Value Estimation of Straw Multifuels for Combined Heat and Power Generation Processes — Accepted by Energies

2024.09: 🎉 Multi-Encoder Feature Fusion Model for Complex Combustion State Recognition — Accepted by CAC

Server

Daniel lewis
quote icon

Daniel lewis

Richard was hired to create a corporate identity. We were very pleased with the work done. She has a lot of experience and is very concerned about the needs of client. Lorem ipsum dolor sit amet, ullamcous cididt consectetur adipiscing elit, seds do et eiusmod tempor incididunt ut laborels dolore magnarels alia.

Resume

Education

  1. Zhejiang University of Technology

    Ph.D. in Control Science and Engineering (Rank: 5/40)
    Core Courses: Matrix Theory, Modern Signal Processing, Optimization, Embedded Artificial Intelligence, Digital Image Processing, Audio-Visual Multimedia Technology, Embedded Systems, Graph Theory and Networks, Computer Vision…

Internships

  1. Sightcare, China.

    2022.05 — 2024.05
    • 1. Conducted research and development of intelligent text analysis algorithms based on deep learning;
    • 2. Developed algorithms for reading order prediction and layout analysis for distorted and tilted pages;
    • 3. Optimized and deployed deep learning algorithms onto AI chips (HiSilicon, Rockchip, Bitmain) for lightweight acceleration;
    • 4. Developed assistive vision products on HiSilicon platforms (Hi3516 DV300/DV500) and Rockchip platforms (RV1126, RK3566);
    • 5. Adapted new sensors (imx214, imx586) for image acquisition modules;
    • 6. Adapted new screens (MIPI, RGB, EDP) for display modules.

  2. Silan, China.

    2020.05 — 2020.09
    • 1. Designed schematic diagrams and layouts for demo boards based on chip manuals and performed soldering and debugging;
    • 2. Conducted high/low-temperature, lightning, and EMI testing;
    • 3. Analyzed test data and completed chip test reports.

    3. Languages

    • Mandarin
      100%
    • English
      80%
    • Deutsch
      60%
    • Cantonese
      10%

    Skills

    • Linux
      80%
    • Pytorch
      70%
    • Python
      80%
    • C/C++
      80%

Publications

  • DiFusionSeg

    Knowledge-Based Systems

    DiFusionSeg: Diffusion-Driven Semantic Segmentation with Multi-Modal Image Fusion for Enhanced Perception

    Paper | Code

  • MAUGIF

    Arxiv

    MAUGIF: Mechanism-Aware Unsupervised General Image Fusion via Dual Cross-Image Autoencoders

    Paper | Code

  • Design conferences in 2022

    Conference on Automation and Control (CAC)

    Multi-Encoder Feature Fusion Model for Complex Combustion State Recognition

    Paper | Code

  • Design conferences in 2022

    Energies

    U-Net Semantic Segmentation-Based Calorific Value Estimation of Straw Multifuels for Combined Heat and Power Generation Processes

    Paper | Code

Projects

Others