Real-Time Variational Range Image Fusion and Visualization for Large-Scale Scenes Using GPU Hash Tables
Abstract
We present a real-time pipeline for large-scale 3D scene reconstruction from a single moving RGB-D camera together with interactive visualization. Our approach combines a time and space efficient data structure capable of representing large scenes, a local variational update algorithm and a visualization system. The environment's structure is reconstructed by integrating the depth image of each camera view into a sparse volume representation using a truncated signed distance function, which is organized via a hash table. Noise from real-world data is efficiently eliminated by immediately performing local variational refinements on newly integrated data. The whole pipeline is able to perform in real-time on consumer-available hardware and allows for simultaneous inspection of the currently reconstructed scene.
Cite
Text
Marniok and Goldluecke. "Real-Time Variational Range Image Fusion and Visualization for Large-Scale Scenes Using GPU Hash Tables." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018. doi:10.1109/WACV.2018.00105Markdown
[Marniok and Goldluecke. "Real-Time Variational Range Image Fusion and Visualization for Large-Scale Scenes Using GPU Hash Tables." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018.](https://mlanthology.org/wacv/2018/marniok2018wacv-real/) doi:10.1109/WACV.2018.00105BibTeX
@inproceedings{marniok2018wacv-real,
title = {{Real-Time Variational Range Image Fusion and Visualization for Large-Scale Scenes Using GPU Hash Tables}},
author = {Marniok, Nico and Goldluecke, Bastian},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2018},
pages = {912-920},
doi = {10.1109/WACV.2018.00105},
url = {https://mlanthology.org/wacv/2018/marniok2018wacv-real/}
}