We are Video & Image Computing Lab at KAIST.

Our research of interest includes deep-learning-based computer vision, computational image & video processing as well as image & video understanding and 2D/3D video coding.

​

Our recent intensive works focus on Computer Vision research in the fields of:

[1] 3D image/video reconstruction: (1) optical flow estimation, (2) camera pose estimation, (3) dynamic neural radiance field (NeRF) and static/dynamic Gaussian Splatting (3D/4D GS) learning of video for novel view synthesis;

[2] image/video generation and editing with visual foundation models: (1) object-level image/video editing, (2) image text editing and style changes,

[3] natural image and video restoration: (1) super-resolution, (2) video frame interpolation and motion deblurring, (3) depth estimation, (4) image deraining, dehazing,and in-painting,

[4] satellite images: (1) PAN sharpening, super-resolution and cloud removal of Electro-Optical (EO) images, (2) super-resolution, detection and classification of Synthetic Aperture Radar (SAR) image targets, (3) SAR-to-EO image-to-image translation learning, (4) remote-sensing visual language models (RS-VLM). 

​