Research Interests

• Deep learning for computer vision tasks

✓ 3D Reconstruction with voxel & point clouds & implicit representations

✓ Image Restoration or Enhancement like super-resolution, image inpainting

✓ Image generation and translation via generative adversarial networks (GAN)

✓ Neural network architecture


News

Oct. 2022 : One paper is accepted in WACV 2023

Feb. 2022 : One paper is accepted in ACMMM 2022

Feb. 2020 : One paper is accepted in CVPR 2020

Jun. 2019 : Two papers are accepted in IROS 2019

May. 2019 : One paper is accepted in RSS 2019


International Conferences

2023

CG-NeRF: Conditional Generative Neural Radiance Fields

Kyungmin Jo*, Gyumin Shim*, Sanghun Jung, Soyoung Yang, Jaegul Choo

*Equal contribution

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2023

[Paper] [Bibtex][Project Page]

2022

ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human Reconstruction

Gyumin Shim*, Minsoo Lee*, Jaegul Choo

*Equal contribution

ACM International Conference on Multimedia (ACMMM), Oct 2022

[Paper] [Bibtex][Project Page]

2020

Robust Reference-based Super-Resolution with Similarity-Aware Deformable Convolution

Gyumin Shim, Jinsun Park and In So Kweon

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2020

[Paper] [Bibtex][Project Page]

2019

Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment

Jinsun Park, Ukcheol Shin, Gyumin Shim, Kyungdon Joo, Francois Rameau, Junhyeok Kim, Dong-Geol Choi and In So Kweon

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nov 2019

[Paper] [Bibtex]

Camera Exposure Control for Robust Robot Vision with Noise-Aware Image Quality Assessment

Ukcheol Shin, Jinsun Park, Gyumin Shim, Francois Rameau and In So Kweon

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nov 2019

[Paper] [Bibtex] [Project Page (Code & Dataset)]

Segment2Regress: Monocular 3D Vehicle Localization in Two Stages

Choe, K Joo, F Rameau, G Shim, IS Kweon

Robotics: Science and Systems (RSS)

[Paper]