Yang Hong-Bin (Petingo)

Portfolio
Github
[email protected]
Lausanne, Switzerland

Education

École Polytechnique Fédérale de Lausanne (EPFL)

M.S. in Computer Science
Sep. 2021 ~ Present

  • GPA 5.4/6.0

Taiwan Tech

B.S. in Computer Science
Sep. 2016 ~ Jun. 2020

  • GPA 4.1/4.3

Czech Technical University in Prague

Exchange Student in the Faculty of Electrical Engineering​
Feb. 2020 ~ Jun. 2020

  • GPA 1.0/1.0

Skill

Technical - Computer Vision, Deep Learning, 3D Geometry Computing, AR, Digital Fabrication

Programming - C, C++, Python, JavaScript, Go, Java

Language - English (C1-C2), German (Beginner), Japanese (Basic), Mandarin (Native)

Professional Experience

IBOIS (Laboratory for Timber Constructions), EPFL

Part-time Student Assistant & Full-time Summer Internship
Apr. 2022 ~ Present

  • Participated in a research project of augmented reality for hand-held carpentry tools.
  • Refined an open-source SLAM method and integrated it into the main program (in C++), including:
    1. Developing new features such as map fusion and 3D model reconstruction
    2. Enabling OpenGL compatibility to fuse the virtual scene and the camera view
    3. Resolving several bugs in the original code to increase the robustness and stability.

Artificial Intelligence and Image Understanding Lab, Academia Sinica

Research Assistant
Jul. 2020 ~ Dec. 2020

  • Explored the possibility of utilizing image quality assessment methods (NIMA and BRISQUE) to enhance the realness of the composite image produced by deep learning-based image harmonization methods (e.g. Deepfake).
  • Re-implemented a deep learning-based image forgery detection method (Face X-ray) in PyTorch and tried to improve it by introducing more features such as DCT and FFT.

Lab of Image/Video Processing and Compression, Taiwan Tech

Student Research Assistant
Jan. 2019 ~ Feb. 2020

  • Conducted research on chroma subsampling and upsampling on both normal photo and light-field images (mainly in Python and Tensorflow 1.0).
  • Proposed an low-distortion YUV420 subsampling method, which outperform the previous state-of-the-art by 1.1dB (2.5%) in the evaluation of PSNR.

STAR BIT Innovation Co.,Ltd.

Software Engineer Intern
Mar. 2018 ~ Jul. 2019

  • Developed front-end APIs of a decentralized cryptocurrency exchange in JavaScript to enable 5 different kinds of Ethereum wallets to interact with the Ethereum blockchain directly through the web interface.
  • Collaborated with KeyXentic and developed a Chrome Extension that enables web3.js support for their hardware wallet.

Publication

H. B. Yang, M. Johanes, F. C. Kim, M. Bernhard, & J. Huang, “Architectural Sketch to 3D Model: An Experiment on Simple-Form Houses,” Under review of CAAD Future 2023

  • Created a synthetic dataset of 3D house models and corresponding hand-drawn sketches with Rhino Grasshopper and trained a deep learning network that can generate a 3D mesh based on a hand-drawn sketch.
  • Built a web-based interface for demonstration, where the user can sketch and view the generated result in a browser.

Chung, K. L., Cheng, J. S., & Yang, H. B. , “Effective Chroma Subsampling and Luma Modification for RGB Full-Color Images Using the Multiple Linear Regression Technique,” IEEE Access, 8, 118315-118323., Jun 2020 (Link to Paper)

  • Proposed the initial idea of applying multiple linear regression on YUV420 subsampling to minimize the distortion.
  • The final result outperformed the previous state-of-the-art by 1.1dB (2.5%) in the evaluation of PSNR.

Honors & Awards

2021 | Special Award of the YearShin Kong Mitsukoshi International Photography Contest

2020 | Study Abroad ScholarshipTaiwan Tech and Ministry of Education, Taiwan

  • Based on English proficiency

2019 | College Student Research ScholarshipMinistry of Science and Technology, Taiwan

  • Based on the research proposal and academic performance
  • Proposed a low-distortion CNN-based chroma upsampling method for light field image, which outperforms the conventional bicubic and bilinear method by 1.24dB (2.9%) and 2.22dB (5.4%), respectively, in the evaluation of PSNR.

2019 | Silver Award – ICPC Taiwan National Contest for Technology Universities

  • Competitive programming contest; preliminary for ACM-ICPC

2018 | 1st PlaceNational Taiwan University System App Innovation Contest

  • Demonstrated a map-based student forum (Android APP, Java)

2018 | Honorable mentionNational Collegiate Programming Contest (Taiwan)

  • Competitive programming contest; preliminary for ACM-ICPC

2017 | Best Presentation AwardIntelligent Living Hackathon

  • Top 6 among 50 teams
  • Demonstrated a management system for a shared refrigerator using an Android phone and student ID.