Daeyun Shin

My research interests are in artificial intelligence at the intersection of computer vision and computer graphics. I am interested in 2D-3D relations and unsupervised learning. I am advised by Derek Hoiem.

Education

2017, M.S. in Computer Science, University of Illinois at Urbana-Champaign

2015, B.S. in Computer Science, University of Illinois at Urbana-Champaign

Publications

3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
Qualitative results
Tanmay Gupta, Daeyun Shin, Naren Sivagnanadasan, Derek Hoiem
arXiv:1606.05002, 2016

Completing 3D Object Shape from One Depth Image
Project page
Jason Rock, Tanmay Gupta, Justin Thorsen, Junyoung Gwak, Daeyun Shin, Derek Hoiem
Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2015

Current topics

• Multiple-view 3D volume learning and reconstruction.
• Multi-task learning.

Projects, Code, tools

• Python library for vision research Code

• Multi-view 3D shape graph cut implementation (Campbell et al.) Code

• Improving Randomzied SVD Code Report

• Off-screen depth and silhouette rendering using OSMesa. Python C

• Saliency for 3D meshes Code Demo

• Extracting informative graphics from packaging designs code/demo

• Modern OpenGL renderer C++ GLSL shader

• Computational photography implementations
  • Video Stitching and Processing
  • Image-based Lighting
  • Gradient-Domain Fusion
  • Image Quilting
  • Hybrid Images

• Modern image annotation toolkit code

• MATLAB utils
  • Load Google Earth KMZ (.kmz) file as a triangular mesh. code
  • Exporting figures code

• Vim and Unix configurations .vimrc, others

• LaTeX templates

• Other stuff on Github: link