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.
@article{arxiv.1807.10376,
title = {Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset},
author = {Qi Guo and Iuri Frosio and Orazio Gallo and Todd Zickler and Jan Kautz},
journal= {arXiv preprint arXiv:1807.10376},
year = {2018}
}