Picture for Munchurl Kim

Munchurl Kim

Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report

Add code
Nov 07, 2022
Figure 1 for Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
Figure 2 for Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
Figure 3 for Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
Figure 4 for Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
Viaarxiv icon

Layered Depth Refinement with Mask Guidance

Add code
Jun 07, 2022
Figure 1 for Layered Depth Refinement with Mask Guidance
Figure 2 for Layered Depth Refinement with Mask Guidance
Figure 3 for Layered Depth Refinement with Mask Guidance
Figure 4 for Layered Depth Refinement with Mask Guidance
Viaarxiv icon

Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos

Add code
May 18, 2022
Figure 1 for Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos
Figure 2 for Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos
Figure 3 for Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos
Figure 4 for Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos
Viaarxiv icon

DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting

Add code
Nov 19, 2021
Figure 1 for DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
Figure 2 for DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
Figure 3 for DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
Figure 4 for DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
Viaarxiv icon

SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery

Add code
May 06, 2021
Figure 1 for SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery
Figure 2 for SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery
Figure 3 for SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery
Figure 4 for SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery
Viaarxiv icon

Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images

Add code
Apr 16, 2021
Figure 1 for Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images
Figure 2 for Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images
Figure 3 for Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images
Figure 4 for Exploiting Global and Local Attentions for Heavy Rain Removal on Single Images
Viaarxiv icon

XVFI: eXtreme Video Frame Interpolation

Add code
Mar 30, 2021
Figure 1 for XVFI: eXtreme Video Frame Interpolation
Figure 2 for XVFI: eXtreme Video Frame Interpolation
Figure 3 for XVFI: eXtreme Video Frame Interpolation
Figure 4 for XVFI: eXtreme Video Frame Interpolation
Viaarxiv icon

PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier

Add code
Mar 29, 2021
Figure 1 for PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
Figure 2 for PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
Figure 3 for PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
Figure 4 for PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
Viaarxiv icon

PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss

Add code
Mar 12, 2021
Figure 1 for PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
Figure 2 for PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
Figure 3 for PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
Figure 4 for PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
Viaarxiv icon

Zoom-to-Inpaint: Image Inpainting with High Frequency Details

Add code
Dec 17, 2020
Figure 1 for Zoom-to-Inpaint: Image Inpainting with High Frequency Details
Figure 2 for Zoom-to-Inpaint: Image Inpainting with High Frequency Details
Figure 3 for Zoom-to-Inpaint: Image Inpainting with High Frequency Details
Figure 4 for Zoom-to-Inpaint: Image Inpainting with High Frequency Details
Viaarxiv icon