Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance measured by average End-Point Error (EPE) has improved over the years, flow estimates are still poorer along motion boundaries (MBs), where the flow is not smooth, as is typically assumed, and where features computed by neural networks are contaminated by multiple motions. To improve flow in the unsupervised settings, we design a framework that detects MBs by analyzing visual changes along boundary candidates and replaces motions close to detections with motions farther away. Our proposed algorithm detects boundaries more accurately than a baseline method with the same inputs and can improve estimates from any flow predictor without additional training.
翻译:以深层学习为基础的不受监督的光学流测算器由于对地面真相的说明的成本和困难而引起越来越多的关注。虽然多年来按平均最终点错误衡量的性能有所改善,但沿运动边界(MBs)的流量估计仍然比较差,因为通常假设流动不平稳,神经网络计算出的特征受到多重动作的污染。为了改善不受监督环境的流量,我们设计了一个框架,通过分析边界候选人的视觉变化来检测MB,用距离更远的动作取代接近探测的运动。我们提议的算法用同样的投入比基线方法更精确地探测边界,并且可以在没有额外培训的情况下改进来自任何流动预测器的估计数。