Search Results for author: Won-Ki Jeong

Found 11 papers, 4 papers with code

I2V: Towards Texture-Aware Self-Supervised Blind Denoising using Self-Residual Learning for Real-World Images

no code implementations21 Feb 2023 Kanggeun Lee, Kyungryun Lee, Won-Ki Jeong

Although the advances of self-supervised blind denoising are significantly superior to conventional approaches without clean supervision in synthetic noise scenarios, it shows poor quality in real-world images due to spatially correlated noise corruption.

Denoising SSIM

MitoVis: A Visually-guided Interactive Intelligent System for Neuronal Mitochondria Analysis

no code implementations3 Sep 2021 Junyoung Choi, Hakjun Lee, Suyeon Kim, Seok-Kyu Kwon, Won-Ki Jeong

It is known that the morphology of mitochondria is closely related to the functions of neurons and neurodegenerative diseases.

ColorRL: Reinforced Coloring for End-to-End Instance Segmentation

no code implementations CVPR 2021 Tran Anh Tuan, Nguyen Tuan Khoa, Tran Minh Quan, Won-Ki Jeong

Instance segmentation, the task of identifying and separating each individual object of interest in the image, is one of the actively studied research topics in computer vision.

Instance Segmentation Semantic Segmentation

ISCL: Interdependent Self-Cooperative Learning for Unpaired Image Denoising

1 code implementation19 Feb 2021 Kanggeun Lee, Won-Ki Jeong

With the advent of advances in self-supervised learning, paired clean-noisy data are no longer required in deep learning-based image denoising.

Image Denoising Self-Supervised Learning

Noise2Kernel: Adaptive Self-Supervised Blind Denoising using a Dilated Convolutional Kernel Architecture

no code implementations7 Dec 2020 Kanggeun Lee, Won-Ki Jeong

In this paper, we propose a dilated convolutional network that satisfies an invariant property, allowing efficient kernel-based training without random masking.

Image Denoising

Reinforced Coloring for End-to-End Instance Segmentation

no code implementations14 May 2020 Tuan Tran Anh, Khoa Nguyen-Tuan, Tran Minh Quan, Won-Ki Jeong

To exploit the advantages of conventional single-object-per-step segmentation methods without impairing the scalability, we propose a novel iterative deep reinforcement learning agent that learns how to differentiate multiple objects in parallel.

Instance Segmentation Semantic Segmentation

Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss

1 code implementation3 Sep 2017 Tran Minh Quan, Thanh Nguyen-Duc, Won-Ki Jeong

In this paper, we propose a novel deep learning-based generative adversarial model, RefineGAN, for fast and accurate CS-MRI reconstruction.

MRI Reconstruction

ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features

no code implementations25 Jul 2017 Inwan Yoo, David G. C. Hildebrand, Willie F. Tobin, Wei-Chung Allen Lee, Won-Ki Jeong

The alignment of serial-section electron microscopy (ssEM) images is critical for efforts in neuroscience that seek to reconstruct neuronal circuits.

Image Registration

FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics

6 code implementations16 Dec 2016 Tran Minh Quan, David G. C. Hildebrand, Won-Ki Jeong

Electron microscopic connectomics is an ambitious research direction with the goal of studying comprehensive brain connectivity maps by using high-throughput, nano-scale microscopy.

Brain Image Segmentation Image Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.