Hello, I'm Ke-Chi Chang.

You can also call me Arc Chang.

I'm a Computer Vision Research Engineer at MediaTek Inc. now. I received the B.S. and M.S. degree in Computer Science from National Tsing-Hua University ,in 2018 and 2020, respectively. I had been in Vision and Learning Lab with Prof. Hwan-Tzong Chen . My research focuses on Computer Vision, Machine Learning, and Generative AI.


Experience

2020/08 - now

MEDIATEK Taiwan | Hsinchu

Computer Vision Algorithm & AI Engineer

Integrate the AI algorithms into low-level and high-level vision tasks. Mainly for highend smartphone project.

  • AI-NR : Denoising on burst images.
  • AI-HDR : Denoising and dynamic range compression on multi-exposure images.
  • AI-Flash : Denoising and dynamic range compression on flash and non-flash pairs.
  • AI-Detection : Includes object and face detection, facial landmark detection, race and age detection.
  • AI-Segmentation : Semantic and instance segmentation tasks.
  • AI-SR : Super resolution by diffusion models.
  • MediaTek ISP Architecture
  • 2019/07 - 2020/06

    MEDIATEK Intern Taiwan | Hsinchu

    Published "Learning Camera-Aware Noise Models" on ECCV 2020 (*Top Conference in AI area)

  • Propose a GAN-based noise model learned from real-world noise and outperform other statistical noise models.
  • Can generate unlimited synthetic noisy images from clean images with different cameras by our noise model.
  • Improve the denoising performance by the combination of real and synthetic pairs.



  • Skills

    Python

    95%

    C/C++

    75%

    PyTorch

    90%

    TensorFlow

    85%



    Language

    Chinese

    95%

    English

    70%

    Taiwanese

    50%



    Copyright © All rights reserved | This template is made by Colorlib