Publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Under Review
    vha.png
    VHA: VQA-based Hallucination Assessment for Generative Image Super-Resolution
    Donghun Ryou, Inju Ha, Jaeyoo Park, and Bohyung Han
    Under Review , Oct 2026
    TL;DR: We present VHA, a VQA-based metric that uses bidirectional visual question answering to assess whether generated super-resolution details remain grounded in the reference image.
  2. CVPR 2026
    beyond.png
    Beyond the Ground Truth: Enhanced Supervision for Image Restoration
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2026
    TL;DR: We present a supervision enhancement framework that generates high-fidelity ground truths by fusing suboptimal references with super-resolved details via frequency-domain mixup.
  3. CVPR 2026
    learning.gif
    Learning to Translate Noise for Robust Image Denoising
    Inju Ha*, Donghun Ryou*, Seonguk Seo, and Bohyung Han
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, Jun 2026
    TL;DR: We present a robust denoising framework that simplifies the removal of complex real-world noise by translating it into Gaussian noise.

2024

  1. CVPR 2024
    afm2.png
    Robust Image Denoising through Adversarial Frequency Mixup
    Donghun Ryou, Inju 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.