Our research areas We are foucing on making multi-modal intelligent systems with AI! Bio-sinspired camera-based vision High-speed and HDR vision problems 360 camera-based vision> Digital human, Neural rendering 3D scene understanding and SLAM Robotics and XR, HCI High-level vision problems Semmantic segmentation, 2D/3D object detection Low-level vision problems HDR imaging, image/video restoration and enhancement Learning methods in vision GANs,self-/semi-supervised learning NeRF-based 3D reconstruction Domain adaptatoin, knowledge transfer Computer vision for AR/Metaverse Avatar generation, Scene modeling and understanding Multi-modal AIGC for Metaverse depth estimation, motion estimation and compensation
