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

[1] AI-based 3D/4D Realistic 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 AIs:

(1) object-level image/video editing, (2) image text editing and style changes,

[3] AI-based Image and Video Restoration and Quality Enhancement:

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

[4] AI-based Image and Video Analysis for Drones and Satellites:

(1) PAN Sharpening, Super-Resolution and Cloud Removal of Satellite 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 Foundation Models and Visual Language Models (RS-VLM) for Satellite Imagery.

​

To see our research work, please visit the site : https://kaist-viclab.github.io/​