论文标题
MaskFlownet：不对称功能与可学习的遮挡面膜匹配
MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
论文作者
论文摘要
特征翘曲是光流估计中的核心技术；但是，在扭曲过程中被阻塞区域引起的歧义是一个尚未解决的主要问题。在本文中，我们提出了一个不对称的闭塞功能匹配模块，该模块可以学习一个粗糙的闭塞面膜，该掩模在特征翘曲后立即过滤（闭塞）区域，而无需任何明确的监督。所提出的模块可以轻松地集成到端到端网络体系结构中，并在引入可忽略的计算成本的同时享有性能提高。学到的遮挡面膜可以进一步送入随后的网络级联，并具有双重特征金字塔，我们可以实现最先进的性能。在提交时，我们的方法称为MaskFlownet，超过了MPI Sintel，Kitti 2012和2015 Benchmarks上所有已发表的光流方法。代码可在https://github.com/microsoft/maskflownet上找到。
Feature warping is a core technique in optical flow estimation; however, the ambiguity caused by occluded areas during warping is a major problem that remains unsolved. In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision. The proposed module can be easily integrated into end-to-end network architectures and enjoys performance gains while introducing negligible computational cost. The learned occlusion mask can be further fed into a subsequent network cascade with dual feature pyramids with which we achieve state-of-the-art performance. At the time of submission, our method, called MaskFlownet, surpasses all published optical flow methods on the MPI Sintel, KITTI 2012 and 2015 benchmarks. Code is available at https://github.com/microsoft/MaskFlownet.
