论文标题
COT-AMFLOW：与无监督光流估计的共同教学策略的自适应调制网络
CoT-AMFlow: Adaptive Modulation Network with Co-Teaching Strategy for Unsupervised Optical Flow Estimation
论文作者
论文摘要
自我运动和场景变化的解释是移动机器人的基本任务。光流信息可用于估计周围环境中的运动。最近，无监督的光流估计已成为研究热点。但是，无监督的方法通常很容易在部分遮挡或无纹理的区域中变得不可靠。为了解决这个问题，我们在本文中提出了COT-AMFLOW，这是一种无监督的光流估计方法。在网络体系结构方面，我们开发了一个自适应调制网络，该网络采用两种新型模块类型，即流量调制模块（FMM）和成本量调制模块（CMMS），以删除具有挑战性的区域中的异常值。至于培训范式，我们采用了一项共同教学策略，在该策略中，两个网络同时互相教导挑战区域以进一步提高准确性。 MPI Sintel，Kitti Flow和Middlebury Flow Benchmarks的实验结果表明，我们的COT-AMFLOW的表现优于所有其他最新的无监督方法，同时仍在实时运行。我们的项目页面可在https://sites.google.com/view/cot-amflow上找到。
The interpretation of ego motion and scene change is a fundamental task for mobile robots. Optical flow information can be employed to estimate motion in the surroundings. Recently, unsupervised optical flow estimation has become a research hotspot. However, unsupervised approaches are often easy to be unreliable on partially occluded or texture-less regions. To deal with this problem, we propose CoT-AMFlow in this paper, an unsupervised optical flow estimation approach. In terms of the network architecture, we develop an adaptive modulation network that employs two novel module types, flow modulation modules (FMMs) and cost volume modulation modules (CMMs), to remove outliers in challenging regions. As for the training paradigm, we adopt a co-teaching strategy, where two networks simultaneously teach each other about challenging regions to further improve accuracy. Experimental results on the MPI Sintel, KITTI Flow and Middlebury Flow benchmarks demonstrate that our CoT-AMFlow outperforms all other state-of-the-art unsupervised approaches, while still running in real time. Our project page is available at https://sites.google.com/view/cot-amflow.
