|2021.08||🔥 We are releasing source codes for KPAC.|
|2021.07||A paper on defocus deblurring (KPAC) is accepted to ICCV 2021.|
|2021.06||We are releasing source codes for IFAN and PVDNet.|
|2021.03||Demos for DMENet and IFAN are released.|
|2021.03||A paper on video deblurring (PVDNet) is accepted to TOG 2021.|
|2021.03||A paper on defocus deblurring (IFAN) is accepted to CVPR 2021.|
|2020.12||We received the presentation award for our paper on defocus deblurring at KSC 2020.|
|2020.10||We are releasing source codes for CTHA.|
|2020.09||A paper on color transfer using histogram analogy (CTHA) is accepted to CGI 2020.|
|2019.11||I won NAVER Ph.D Fellowship.|
|2019.06||We are releasing source codes for DMENet and SYNDOF.|
|2019.03||A paper on defocus map estimation is accepted to CVPR 2019.|
The error usually occurs when Nvidia driver is newly installed or docker/nvidia-docker is installed.
When nvidia-smi prints out an output slowly, the following command may by useful:
This post summarizes my deep learning environment setting on freshly installed Ubuntu16.04.
While using git, it is annoying to type a password or passphrase when there are frequent commits/pushes.
Solution for docker error,
ImportError: libGL.so.1: cannot open shared object file: No such file or directory
When we pull a docker image from the dockerhub, the container sometimes throws an error regarding libGL.so.1:
This post introduces the installation procedure for the docker (community edition) as well as nvidia-docker v1.0.1.
Docker hub is very useful for maintaining images, especially when working with many machines with the same image.