68 citations · 106 across the 12 of their papers we have counts for
14 papers
LoViF 2026 The First Challenge on Unified Removal of Raindrops and Reflections: Methods and Results
Zewei He, Xi Tong, Yu Chen +49
This workshop paper comprehensively reviews the First Challenge on Unified Removal of Raindrops and Reflections. The challenge aims to address a frequently encountered practical pr…
Dataset Distillation for Super-Resolution without Class Labels and Pre-trained Models
Sunwoo Cho, Yejin Jung, Nam Ik Cho +1
Training deep neural networks has become increasingly demanding, requiring large datasets and significant computational resources, especially as model complexity advances. Data dis…
Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution
Karam Park, Jae Woong Soh, Nam Ik Cho
Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to…
Training Patch Analysis and Mining Skills for Image Restoration Deep Neural Networks
Jae Woong Soh, Nam Ik Cho
There have been numerous image restoration methods based on deep convolutional neural networks (CNNs). However, most of the literature on this topic focused on the network architec…
Variational Deep Image Restoration
Jae Woong Soh, Nam Ik Cho
This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described…
A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution
Karam Park, Jae Woong Soh, Nam Ik Cho
Deep learning methods have shown outstanding performance in many applications, including single-image super-resolution (SISR). With residual connection architecture, deeply stacked…
Variational Deep Image Denoising
Jae Woong Soh, Nam Ik Cho
Convolutional neural networks (CNNs) have shown outstanding performance on image denoising with the help of large-scale datasets. Earlier methods naively trained a single CNN with…
Deep Universal Blind Image Denoising
Jae Woong Soh, Nam Ik Cho
Image denoising is an essential part of many image processing and computer vision tasks due to inevitable noise corruption during image acquisition. Traditionally, many researchers…
Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
Yoonsik Kim, Jae Woong Soh, Gu Yong Park +1
Real-noise denoising is a challenging task because the statistics of real-noise do not follow the normal distribution, and they are also spatially and temporally changing. In order…
Meta-Transfer Learning for Zero-Shot Super-Resolution
Jae Woong Soh, Sunwoo Cho, Nam Ik Cho
Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable perfor…
Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination
Jae Woong Soh, Gu Yong Park, Junho Jo +1
Recently, many convolutional neural networks for single image super-resolution (SISR) have been proposed, which focus on reconstructing the high-resolution images in terms of objec…
Handwritten Text Segmentation via End-to-End Learning of Convolutional Neural Network
Junho Jo, Hyung Il Koo, Jae Woong Soh +1
We present a new handwritten text segmentation method by training a convolutional neural network (CNN) in an end-to-end manner. Many conventional methods addressed this problem by…
Joint High Dynamic Range Imaging and Super-Resolution from a Single Image
Jae Woong Soh, Jae Sung Park, Nam Ik Cho
This paper presents a new framework for jointly enhancing the resolution and the dynamic range of an image, i.e., simultaneous super-resolution (SR) and high dynamic range imaging…
Generation of High Dynamic Range Illumination from a Single Image for the Enhancement of Undesirably Illuminated Images
Jae Sung Park, Nam Ik Cho
This paper presents an algorithm that enhances undesirably illuminated images by generating and fusing multi-level illuminations from a single image.The input image is first decomp…