Ka Leong Cheng

I am a PhD candidate at Visual Intelligence Lab, part of the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST). My supervisor is Dr. Qifeng Chen. I passed my PhD Qualification Exam (PQE) on July 22 in 2022.

I received my BEng degree in Computer Science and Engineering and BBA degree in General Business Management at the Hong Kong University of Science and Technology (HKUST) in 2020.

Email  /  Google Scholar  /  Github  /  LinkedIn

profile photo
Research

* indicates joint first author; indicates corresponding author

Learning Naturally Aggregated Appearance for Efficient 3D Editing
Ka Leong Cheng, Qiuyu Wang, Zifan Shi, Kecheng Zheng, Yinghao Xu, Hao Ouyang,
Qifeng Chen, Yujun Shen
Arxiv Preprint
arXiv / bibtex / code / project page

We propose an editing-friendly representation AGAP, which supports various 3D editing by applying different 2D image processing tools on the canonical images without need for re-optimization.

Hyperthumbnail: Real-time 6K Image Rescaling with Rate-distortion Optimization
Chenyang Qi*, Xin Yang*, Ka Leong Cheng, Ying-Cong Chen, Qifeng Chen
Computer Vision and Pattern Recognition Conference (CVPR), 2023
arXiv / bibtex / code / project page

We propose Hyperthumbnail to do image upscaling with learnable frequency-domain quantization and achieve 6K real-time speed with best rate-distortion.

Optimizing Image Compression via Joint Learning with Denoising
Ka Leong Cheng*, Yueqi Xie*, Qifeng Chen
European Conference on Computer Vision (ECCV), 2022
arXiv / bibtex / code

We optimize the image compression methods on noisy images via joint learning with denoising.

IICNet: A Generic Framework for Reversible Image Conversion
Ka Leong Cheng*, Yueqi Xie*, Qifeng Chen
International Conference on Computer Vision (ICCV), 2021
arXiv / bibtex / code / presentation / supp / supp video

We present the first generic framework for various reversible image conversion (RIC) tasks.

Enhanced Invertible Encoding for Learned Image Compression
Yueqi Xie*, Ka Leong Cheng*, Qifeng Chen
ACM International Conference on Multimedia (ACM MM), 2021
Full Oral Presentation (9% acceptance rate)
arXiv / bibtex / code

We present an enhanced Invertible Encoding Network for learned image compression.

Fully Convolutional Networks for Continuous Sign Language Recognition
Ka Leong Cheng, Zhaoyang Yang, Qifeng Chen, Yu-Wing Tai
European Conference on Computer Vision (ECCV), 2020
arXiv / bibtex

We present a fully convolutional network for online sign language recognition (SLR). This work was done during my research intern in Tencent YouTu X-Lab.

Experiences
  • Research Intern (supervised by Dr. Yujun Shen), Ant Research, Present
  • Junior Research Assistant (supervised by Dr. Qifeng Chen), HKUST, 2020
  • Research Intern (supervised by Prof. Yu-Wing Tai), Tencent YouTu X-Lab, 2019
  • PKU Summer School International, Peking University, 2018
  • Undergraduate Outbound Exchange Program, ETH Zürich, 2018
  • Penn Summer Global Institute, University of Pennsylvania, 2017
Honors and Awards
  • HKUST RedBird Academic Excellence Award for Continuing PhD Students, 2022
  • Hong Kong PhD Fellowship Award, 2021-2024
  • Hong Kong University of Science and Technology Academic Achievement Medal, 2020
  • Technology and Management Elite Student Scholarship, 2019
  • High Fashion Charitable Foundation Exchange Scholarship, 2017
  • Shanghai Commercial Bank Scholarship, 2016
  • University's Scholarship Scheme for Continuing Undergraduate Students, 2016, 2018, 2019
Teaching Assistants
  • COMP 3111: Software Engineering (Fall 2021)
  • COMP 1001: Exploring Multimedia and Internet Computing (Spring 2021)

Thank You ⭐  Dr. Jon Barron