Inju Ha

ECE, SNU, Seoul, Republic of Korea. hij1112 at snu.ac.kr

prof_pic.jpg

Hi, I am a 1st year MSc student in Seoul National University, majoring in Electrical & Computer Engineering. I am currently working in Computer Vision Lab, under the supervision of Prof. Bohyung Han. My research interests is in computer vision tasks, mainly image/video enhancement via neural network. Currently, I am also interested in building generative vision models.

My ambition is to develop visionary models that provide assistance to individuals in ways that are perceived as magical. If you have any inquiries or wish to connect for professional purposes, please do not hesitate to reach out to me at hij1112 at snu.ac.kr. I welcome all correspondence and look forward to hear from you. Wish you a wonderful day!

News

Dec 12, 2024 Our paper Learning to Translate Noise for Robust Image Denoising is archived.
Sep 01, 2024 I joined SNU Computer Vision Lab as a MSc student.
Feb 26, 2024 Our paper Robust Image Denoising through Adversarial Frequency Mixup is accepted to CVPR 2024.

Selected Publications

*denotes equal contribution
  1. arXiv
    learning.gif
    Learning to Translate Noise for Robust Image Denoising
    Inju Ha*Donghun Ryou*Seonguk Seo, and Bohyung Han
    arXiv preprint, Dec 2024
    TL;DR: We present a robust denoising framework that simplifies the removal of complex real-world noise by translating it into Gaussian noise.
  2. CVPR 2024
    afm2.png
    Robust Image Denoising through Adversarial Frequency Mixup
    Donghun RyouInju Ha, Hyewon Yoo, Dongwan Kim, and Bohyung Han
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024
    TL;DR: We present Adversarial Frequency Mixup (AFM), a novel training framework that enhances image denoising networks’ robustness to out-of-distribution noise.