Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera

Kim, Hyomin; Kim, Jungeon; Nam, Hyeonseo; Park, Jaesik; Lee, Seungyong

Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera

Files

v40i2pp523-535.pdf (9.36 MB)

paper1132.mp4 (103.38 MB)

Date

2021

Authors

Kim, Hyomin
Kim, Jungeon
Nam, Hyeonseo
Park, Jaesik
Lee, Seungyong

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

This paper presents an effective method for generating a spatiotemporal (time-varying) texture map for a dynamic object using a single RGB-D camera. The input of our framework is a 3D template model and an RGB-D image sequence. Since there are invisible areas of the object at a frame in a single-camera setup, textures of such areas need to be borrowed from other frames. We formulate the problem as an MRF optimization and define cost functions to reconstruct a plausible spatiotemporal texture for a dynamic object. Experimental results demonstrate that our spatiotemporal textures can reproduce the active appearances of captured objects better than approaches using a single texture map.

        @article{10.1111:cgf.142652
,
journal = {Computer Graphics Forum},
title = {{Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera
}},
author = {Kim, Hyomin and 
Kim, Jungeon and 
Nam, Hyeonseo and 
Park, Jaesik and 
Lee, Seungyong
},
year = {2021
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.142652
}
}