Search Results for author: Tae Hyun Kim

Found 19 papers, 5 papers with code

Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution

1 code implementation15 Mar 2022 Jinsu Yoo, TaeHoon Kim, Sihaeng Lee, Seung Hwan Kim, Honglak Lee, Tae Hyun Kim

Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks.

Image Restoration Super-Resolution

Restore from Restored: Single-image Inpainting

no code implementations25 Oct 2021 Eunhye Lee, Jeongmu Kim, Jisu Kim, Tae Hyun Kim

Recent image inpainting methods have shown promising results due to the power of deep learning, which can explore external information available from the large training dataset.

Image Inpainting

Self-Supervised Adaptation for Video Super-Resolution

1 code implementation18 Mar 2021 Jinsu Yoo, Tae Hyun Kim

Recent single-image super-resolution (SISR) networks, which can adapt their network parameters to specific input images, have shown promising results by exploiting the information available within the input data as well as large external datasets.

Image Super-Resolution Knowledge Distillation +1

Restore from Restored: Single-image Inpainting

no code implementations16 Feb 2021 Eunhye Lee, Jeongmu Kim, Jisu Kim, Tae Hyun Kim

Recent image inpainting methods show promising results due to the power of deep learning, which can explore external information available from a large training dataset.

Image Inpainting

Progressive Image Super-Resolution via Neural Differential Equation

no code implementations22 Jan 2021 Seobin Park, Tae Hyun Kim

We propose a new approach for the image super-resolution (SR) task that progressively restores a high-resolution (HR) image from an input low-resolution (LR) image on the basis of a neural ordinary differential equation.

Image Restoration Image Super-Resolution

Deep Motion Blind Video Stabilization

no code implementations19 Nov 2020 Muhammad Kashif Ali, Sangjoon Yu, Tae Hyun Kim

Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation.

Frame Motion Estimation +1

Scene-Adaptive Video Frame Interpolation via Meta-Learning

1 code implementation CVPR 2020 Myungsub Choi, Janghoon Choi, Sungyong Baik, Tae Hyun Kim, Kyoung Mu Lee

Finally, we show that our meta-learning framework can be easily employed to any video frame interpolation network and can consistently improve its performance on multiple benchmark datasets.

Frame Meta-Learning +1

Restore from Restored: Single Image Denoising with Pseudo Clean Image

no code implementations9 Mar 2020 Seunghwan Lee, Dongkyu Lee, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim

However, these methods have limitations in using internal information available in a given test image.

Image Denoising

Restore from Restored: Video Restoration with Pseudo Clean Video

no code implementations CVPR 2021 Seunghwan Lee, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim

We analyze the restoration performance of the fine-tuned video denoising networks with the proposed self-supervision-based learning algorithm, and demonstrate that the FCN can utilize recurring patches without requiring accurate registration among adjacent frames.

Denoising Optical Flow Estimation +3

Self-Supervised Fast Adaptation for Denoising via Meta-Learning

no code implementations9 Jan 2020 Seunghwan Lee, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim

Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information available from the given input (i. e., internal statistics) at test time.

Denoising Meta-Learning

Fast Adaptation to Super-Resolution Networks via Meta-Learning

1 code implementation ECCV 2020 Seobin Park, Jinsu Yoo, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim

In the training stage, we train the network via meta-learning; thus, the network can quickly adapt to any input image at test time.

Meta-Learning Super-Resolution

Fast and Full-Resolution Light Field Deblurring using a Deep Neural Network

no code implementations31 Mar 2019 Jonathan Samuel Lumentut, Tae Hyun Kim, Ravi Ramamoorthi, In Kyu Park

Restoring a sharp light field image from its blurry input has become essential due to the increasing popularity of parallax-based image processing.

Deblurring

Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring

1 code implementation CVPR 2017 Seungjun Nah, Tae Hyun Kim, Kyoung Mu Lee

To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear.

Ranked #13 on Deblurring on RealBlur-R (trained on GoPro) (SSIM (sRGB) metric)

Deblurring Image Deblurring

Occlusion-Aware Video Deblurring with a New Layered Blur Model

no code implementations29 Nov 2016 Byeongjoo Ahn, Tae Hyun Kim, Wonsik Kim, Kyoung Mu Lee

We also provide a novel analysis on the blur kernel at object boundaries, which shows the distinctive characteristics of the blur kernel that cannot be captured by conventional blur models.

Deblurring

Dynamic Scene Deblurring using a Locally Adaptive Linear Blur Model

no code implementations14 Mar 2016 Tae Hyun Kim, Seungjun Nah, Kyoung Mu Lee

We infer bidirectional optical flows to handle motion blurs, and also estimate Gaussian blur maps to remove optical blur from defocus in our new blur model.

Deblurring Optical Flow Estimation

Generalized Video Deblurring for Dynamic Scenes

no code implementations CVPR 2015 Tae Hyun Kim, Kyoung Mu Lee

We propose a video deblurring method to deal with general blurs inherent in dynamic scenes, contrary to other methods.

Deblurring Optical Flow Estimation

Segmentation-Free Dynamic Scene Deblurring

no code implementations CVPR 2014 Tae Hyun Kim, Kyoung Mu Lee

Thus, we propose a new energy model simultaneously estimating motion flow and the latent image based on robust total variation (TV)-L1 model.

Deblurring Motion Segmentation

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