中文

Qihang Zhang

I am a 2nd-year Master’s student specializing in computational photography and low-level vision at CUHKSZ, advised by Prof. Qilin Sun. I earned my B.E. in Computer Science and Engineering at CUHKSZ.

I am currently a Research Assistant at the Tokyo Institute of Technology, supervised by Prof. Masayuki Tanaka and Prof. Yusuke Monno.

My research interests include:

Applications: Image Processing, HDR Imaging, Novel Sensors
Technologies: Computational Photography, Low-Level Vision

Email  /  CV  /  Github

Work Experience

Vivo

• Test Engine Dev.

• 2022.06 ~ 2022.11

Work Details (Click to expand/collapse)

• Developed and maintained the android test engine, completed the development and implementation of multiple automated test components, and achieved excellent results in improving test efficiency and coverage rate

• Extended the engine usage documents according to the development content, improved the work efficiency of the test team, and reduce the communication time

• Ensured that the test engine could support customized testing needs for different countries, and understood the cultural uniqueness of different regions during the development process

• Fulfilled with Google’s test engineering requirements to automate the entire process of using Google’s Android test benchmarks for mobile phones

Research

Feel free to drop me an email if you're interested in my research.

Research Image
Joint Polarized Image Demosaicing AND Denoising
Qihang Zhang, Masayuki Tanaka, Yusuke Monno
2025.04 ~ 2025.09
ProjectPage
Details (Click to expand/collapse)

• Proposed the first joint denoising and demosaicing framework for color-polarized imaging, addressing both degradations within a shared feature space.

• Designed an encoder-based feature fusion mechanism to enhance reconstruction quality.

• Built a real-world paired polarized image dataset to support model training and evaluation.

Outperformed existing methods across multiple metrics.

Research Image
Ultra-high Dynamic Range Sensor Fast Tone Mapping and ISP
Qihang Zhang, Qilin Sun, PointSpread Technology
2024.05 ~ 2024.11
Details (Click to expand/collapse)

• Design a hardware-based tone mapping algorithm to achieve LDR display of Ultra-HDR images which have dynamic range close to the human eye (130-140dB)

• Implement an end-to-end learnable simplified ISP algorithm that utilizes a small neural network to estimate the global tone mapping parameters for an image, enabling real-time estimation on a 24-bit video stream

• Incorporate end-to-end differentiability in the design of the ISP algorithm to guarantee future expandability. For example, the ISP’s output image can be adapted for target detection tasks, enabling joint optimization between the ISP and the corresponding task, thereby enhancing the output metrics

Research Image
RGB-IR Sensor ISP and Fast Reflection Removal
Qihang Zhang
2023.08 ~ 2023.12
Details (Click to expand/collapse)

• Implement GPU-based RGB-IR sensor image ISP

• Design reflection removal algorithm based on the low reflection property of glass to infrared light, use infrared band information to remove the reflection of the visible light band and provide better multi-spectral images.

• Utilize guided filter to accelerate the feature extraction and fusion from RGB-IR image

Project Experience

Research Image
Camera Image Simulation Pipeline (Huawei Collaboration)
Qihang Zhang & Qilin Sun & Others in Lab of CUHKSZ & Huawei(Sponsoring organization)
2024.08 ~ 2024.11 ~ Present
Details (Click to expand/collapse)

• Designed and implemented a full-stack simulation pipeline modeling the camera imaging process from optics to sensor.

• Applied spatially varying Point Spread Function (PSF) kernels to simulate lens-induced degradation across the image.

• Built a sensor noise modeling framework to generate realistic pixel-level noise maps.

• Delivered an extensible and modular pipeline that can be adapted to different sensors/lenses, providing high-fidelity synthetic raw data for algorithm development and validation.

Parallel Computing Project Image
Parallel Computing Operator Template: CPU/GPU Operator Implementations (CUDA, Triton, MPI, OpenMP)
Qihang Zhang & Yuan Xu
2024.09 ~ 2024.12
Code(Served as a Teaching Assistant)
Details (Click to expand/collapse)

• Built a modular CPU/GPU parallel operator library including image operators (grayscale, blur, Sobel), matrix multiplication, and DNN layers (convolution, fully connected) with backpropagation support.

• Optimized CPU kernels using MPI, Pthreads, OpenMP, and developed high-performance GPU kernels using CUDA and Triton.

• Triton/CUDA implementations of image operators and matrix multiplication outperformed baseline PyTorch eager implementations under equivalent settings.

Research Image
HDR Plus Based HDR Video Processing Application Demo
Qihang Zhang
2022.12 ~ 2023.03
ProjectPage Code
Details (Click to expand/collapse)

• Implemented a high dynamic range (HDR) video processing pipeline based on Google's HDR+ paper, utilizing multi-frame short-exposure RAW synthesis.

• Integrated HDR+ ISP modules including multi-frame alignment and fusion, filtering for noise reduction, and local tone mapping.

• Developed a graphical user interface (GUI) application using Python and PyQt5 framework for user-friendly operation, supporting RAW image sequence selection and processing, with FFmpeg integration for final HDR video synthesis.

Education

The Chinese University of Hong Kong, Shenzhen, China

• M.Phil in Computer Science

• 2023 ~ Present

Tokyo Institute of Technology, Tokyo, Japan

• Research Assistant

• 2025.04 ~ 2025.09

The Chinese University of Hong Kong, Shenzhen, China

• B.E in Computer Science and Engineering

• 2019 ~ 2023

Service

Teaching Assistant - Parallel Computing (CSC4050) | 2024 Fall
Teaching Assistant - Computational Laboratory (CSC1002) | 2024 Spring
Teaching Assistant - Database System (CSC3170) | 2023 Fall
Volunteer - Office of Student Affairs, CUHKSZ | 2020

Template from Jon Barron