论文标题
liteflownet3：解决对应的歧义，以进行更准确的光流估计
LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
论文作者
论文摘要
深度学习方法在解决光流估计问题方面取得了巨大成功。成功的关键在于使用成本量和粗到精细的流量推断。但是，当图像中存在部分阻塞或均匀的区域时，匹配的问题变得不足。这会导致成本量包含异常值并影响其流量解码。此外，粗到最新的流动推断需要准确的流量初始化。模棱两可的对应关系产生错误的流场，并影响随后水平的流动推断。在本文中，我们介绍了一个由两个专用模块组成的深网LiteFlownet3，以应对上述挑战。 （1）我们通过在流量解码之前通过自适应调制修改每个成本向量来改善成本量的离群值问题。 （2）我们通过探索局部流量一致性进一步提高流量准确性。为此，每种不准确的光流都被附近位置的精确旋转替换为流动场的翘曲。 LiteFlownet3不仅可以在公共基准上取得令人鼓舞的结果，而且还具有较小的型号和快速运行时。
Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed when partially occluded or homogeneous regions exist in images. This causes a cost volume to contain outliers and affects the flow decoding from it. Besides, the coarse-to-fine flow inference demands an accurate flow initialization. Ambiguous correspondence yields erroneous flow fields and affects the flow inferences in subsequent levels. In this paper, we introduce LiteFlowNet3, a deep network consisting of two specialized modules, to address the above challenges. (1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.
