Inju Ha

2 accepted papers

2026

Beyond the Ground Truth: Enhanced Supervision for Image Restoration

Donghun Ryou, Inju Ha, Sanghyeok Chu, Bohyung Han

CVPR 2026

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of ground-truth images in datasets due to practical constraints in data acquisition. To address this limitation, we propose a novel fr

Cited by 0 Source ↗Scholar ↗

2024

Robust Image Denoising through Adversarial Frequency Mixup

Donghun Ryou, Inju Ha, Hyewon Yoo, Dongwan Kim, Bohyung Han

CVPR 2024poster

Image denoising approaches based on deep neural networks often struggle with overfitting to specific noise distributions present in training data. This challenge persists in existing real-world denoising networks which are trained using a limited spectrum of real noise distributions and thus show po…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗