Jungeon Kim (김준건)
I am a Ph.D. student in the Computer Graphics Lab at POSTECH , South Korea, where I am advised by
Prof. Seungyong Lee .
My research interest is at the intersection of computer vision, computer graphics, and machine learning areas, especially interested in reconstructing the 3D geometry and appearance of scenes (or objects). Below is the list of selected papers.
Email  / 
CV  / 
Google Scholar  / 
Github
2024
[TOP]  
Deep Cost Ray Fusion for Sparse Depth Video Completion
Jungeon Kim ,
Soongjin Kim ,
Jaesik Park ,
Seungyong Lee
European Conference on Computer Vision (ECCV ), 2024
arXiv /
video /
paper /
supp
We produce a quality completed depth video by effectively fusing per-frame cost volumes constructed from input RGB and sparse depth videos.
2022
[TOP]  
LaplacianFusion: Detailed 3D Clothed-Human Body Reconstruction
Hyomin Kim ,
Hyeonseo Nam ,
Jungeon Kim ,
Jaesik Park ,
Seungyong Lee
ACM Transactions on Graphics (TOG ), 2022 (Proc. SIGGRAPH Asia 2022 )
paper /
code /
video [FF] /
video [supp] /
[TOP]  
CostDCNet: Cost Volume based Depth Completion for a Single RGB-D Image
Jaewon Kam ,
Jungeon Kim ,
Soongjin Kim ,
Jaesik Park ,
Seungyong Lee
European Conference on Computer Vision (ECCV ), 2022
paper /
supp /
code
We complete an input depth image of sparse measurements effectively and efficiently by constructing a cost volume tailored to single-view depth completion task
[TOP]  
Realistic Blur Synthesis for Learning Image Deblurring
Jaesung Rim ,
Geonung Kim ,
Jungeon Kim ,
Junyong Lee ,
Seungyong Lee ,
Sunghyun Cho
European Conference on Computer Vision (ECCV ), 2022
project page /
paper /
code
We create the RSBlur, a novel dataset with real blurred image sequences and the corresponding sharp ones. We show that network training with realistic blurred images improves deblurring performance on real deblurred images.
Your browser does not support the video tag.
[TOP]  
TextureMe: High-quality Textured Scene Reconstruction in Real Time
Jungeon Kim ,
Hyomin Kim ,
Hyeonseo Nam ,
Jaesik Park ,
Seungyong Lee
ACM Transactions on Graphics (TOG ), 2022 (presented at SIGGRAPH 2022 )
paper /
video
We propose a novel framework that simultaneously reconstructs the geometry and texture map of a scene in real time. Thanks to the effective framework design and our image warping field estimation, we consequently can reconstruct a sharp textured 3D model in real time.
2021
[TOP]  
Deep Virtual Markers for Articulated 3D Shapes
Hyomin Kim ,
Jungeon Kim ,
Jaewon Kam ,
Jaesik Park ,
Seungyong Lee
International Conference on Computer Vision (ICCV ), 2021   (Oral Presentation)
paper /
code
Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera
Hyomin Kim ,
Jungeon Kim ,
Hyeonseo Nam ,
Jaesik Park ,
Seungyong Lee
Computer Graphics Forum (Proc. Eurographics ), 2021
paper
2019
Your browser does not support the video tag.
Global Texture Mapping for Dynamic Objects
Jungeon Kim ,
Hyomin Kim ,
Jaesik Park ,
Seungyong Lee
Computer Graphics Forum (Proc. Pacific graphics ), 2019
paper /
video
2018
Semantic Reconstruction: Reconstruction of Semantically Segmented 3D Meshes via Volumetric Semantic Fusion
Junho Jeon ,
Jinwoong Jung ,
Jungeon Kim ,
Seungyong Lee
Computer Graphics Forum (Proc. Pacific graphics ), 2018
paper /
2016
Frame Rate Upconversion Using Pyramid Structure and Dense Motion Vector Fields
Jun-Geon Kim ,
Daeho Lee
Journal of Electronic Imaging (JEI) in SPIE, 2016
Body Segmentation using Gradient Background and Intra-Frame Collision Responses for Markerless Camera-Based Games
Jun-Geon Kim ,
Daeho Lee
Journal of Electrical Engineering & Technology (JEET), 2016