We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2. Our method integrates architecture improvements from supervised optical flow, i.e. the RAFT model, with new ideas for unsupervised learning that include a sequence-aware self-supervision loss, a technique for handling out-of-frame motion, and an approach for learning effectively from multi-frame video data while still only requiring two frames for inference.

翻译：我们提出SMURF,这是一种未经监督的光学流学方法,它改进了所有基准的先进水平,即36美元至40美元(比先前最佳的UFLow方法高),甚至优于若干受监督的方法,如PWC-Net和FlowNet2。 我们的方法结合了由监督的光学流改进的结构,即RAFT模型,并提出了未经监督的学习新想法,其中包括序列自视损失、处理机体外运动的技术,以及从多框架视频数据中有效学习的方法,但仍然只需要两个推断框架。