Accurate motion and depth recovery is important for many robot vision tasks including autonomous driving. Most previous studies have achieved cooperative multi-task interaction via either pre-defined loss functions or cross-domain prediction. This paper presents a multi-task scheme that achieves mutual assistance by means of our Flow to Depth (F2D), Depth to Flow (D2F), and Exponential Moving Average (EMA). F2D and D2F mechanisms enable multi-scale information integration between optical flow and depth domain based on differentiable shallow nets. A dual-head mechanism is used to predict optical flow for rigid and non-rigid motion based on a divide-and-conquer manner, which significantly improves the optical flow estimation performance. Furthermore, to make the prediction more robust and stable, EMA is used for our multi-task training. Experimental results on KITTI datasets show that our multi-task scheme outperforms other multi-task schemes and provide marked improvements on the prediction results.
@article{arxiv.2208.11993,
title = {A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimation},
author = {Yu Chen and Xu Cao and Xiaoyi Lin and Baoru Huang and Xiao-Yun Zhou and Jian-Qing Zheng and Guang-Zhong Yang},
journal= {arXiv preprint arXiv:2208.11993},
year = {2022}
}