9 papers
YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation
Jaekyun Ko, Byung Wan Lim, Soomin Lee +2
Real-world sRGB image denoising remains challenging due to the nonlinear characteristics of sensor noise and the difficulty of acquiring aligned clean-noisy image pairs. Supervised…
PRISM: Latent Composition Consistency for Single-Image Reflection Removal
Junseong Shin, Tae Hyun Kim
Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections -- a severely ill-posed problem. Existing methods operate in…
Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
Jaekyun Ko, Dongjin Kim, Soomin Lee +2
Denoising in the sRGB image space is challenging due to large noise variability. Although end-to-end methods perform well, their effectiveness in real-world scenarios is limited by…
UCMNet: Uncertainty-Aware Context Memory Network for Under-Display Camera Image Restoration
Daehyun Kim, Youngmin Kim, Yoon Ju Oh +1
Under-display cameras (UDCs) allow for full-screen designs by positioning the imaging sensor underneath the display. Nonetheless, light diffraction and scattering through the vario…
Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution
Hyeonjae Kim, Dongjin Kim, Eugene Jin +1
While deep learning-based super-resolution (SR) methods have shown impressive outcomes with synthetic degradation scenarios such as bicubic downsampling, they frequently struggle t…
Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification
Xiaojiao Xiao, Qinmin Vivian Hu, Tae Hyun Kim +1
Liver tumor segmentation, dynamic enhancement regression, and classification are critical for clinical assessment and diagnosis. However, no prior work has attempted to achieve the…