Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset

Qi Guo, Iuri Frosio, Orazio Gallo, Todd Zickler, Jan Kautz; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 368-383

Abstract


Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras. We propose a two-stage, deep-learning approach to address all of these sources of artifacts simultaneously. We also introduce FLAT, a synthetic dataset of 2000 ToF measurements that capture all of these nonidealities, and allows to simulate different camera hardware. Using the Kinect 2 camera as a baseline, we show improved reconstruction errors over state-of-the-art methods, on both simulated and real data.

Related Material


[pdf]
[bibtex]
@InProceedings{Guo_2018_ECCV,
author = {Guo, Qi and Frosio, Iuri and Gallo, Orazio and Zickler, Todd and Kautz, Jan},
title = {Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}