Abstract
Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance degrades at regions where repetitive textures or occlusions occur. In this paper, we propose Deep Epipolar Flow, an unsupervised optical flow method which incorporates global geometric constraints into network learning. In particular, we investigate multiple ways of enforcing the epipolar constraint in flow estimation. To alleviate a ``chicken-and-egg'' type of problem encountered in dynamic scenes where multiple motions may be present, we propose a low-rank constraint as well as a union-of-subspaces constraint for training. Experimental results on various benchmarking datasets show that our method achieves competitive performance compared with supervised methods and outperforms state-of-the-art unsupervised deep-learning methods.
Abstract (translated)
光流计算的无监督深度学习取得了良好的效果。现有的深网训练方法大多依赖于图像亮度一致性和局部平滑约束。在出现重复纹理或闭塞的区域,它们的性能会降低。本文提出了一种将全局几何约束引入网络学习的无监督光流方法——深表极流。特别地,我们研究了在流量估计中实施极性约束的多种方法。为了缓解动态场景中可能存在多个运动的“鸡和蛋”类问题,我们提出了一个低阶约束和一个训练子空间约束的联合。在各种基准数据集上的实验结果表明,与监督方法相比,我们的方法具有竞争力,优于最先进的无监督深度学习方法。
URL
https://arxiv.org/abs/1904.03848