Recent News

 2021.03  🔥 Demos for DMENet and IFAN are released.
 2021.03  A paper on video deblurring is accepted to TOG 2021.
 2021.03  A paper on defocus deblurring is accepted to CVPR 2021.
 2021.01  We received the presentation award for our paper on defocus deblurring at KSC 2020.
 2020.10  We are releasing the source code for the paper on color transfer using histogram analogy.
 2020.09  A paper on color transfer 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.

Recent Posts

How to install nvcc for conda-installed PyTorch in Ubuntu

less than 1 minute read

When we install PyTorch using conda (e.g.,conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch), it incompletly installs the cudatoolkit, which means that we cannot use nvcc provided by the cudatoolkit.

How to use LMDB with PyTorch DataLoader and DistributedDataParallel

1 minute read

Since LMDB cannot be pickled, an error, ...can't pickle Environment Object..., occurs when we naively implement LMDB into data.dataset while wrapping data.DataLoader with Distributed Data Parallel(DDP). To resolve the error, we need to delay the loading of LMDB environment in ...

[Research] Visually understanding DoF with the thins lens model

6 minute read

Please contact me if there is any inaccurate content in this article. I believe the thin lens model is the most straightforward way to understand how the depth of field (DoF) is formed within a camera. We may simplify a complex lens model using the thin lens model for DoF to ...

Dotdrop workflow

1 minute read

I use dotdrop for managing my dotfiles (.zshrc, .vimrc, .tmux.conf, etc.)