Unsupervised optical flow estimation is especially hard near occlusions and motion boundaries and in low-texture regions. We show that additional information such as semantics and domain knowledge can help better constrain this problem. We introduce SemARFlow, an unsupervised optical flow network designed for autonomous driving data that takes estimated semantic segmentation masks as additional inputs. This additional information is injected into the encoder and into a learned upsampler that refines the flow output. In addition, a simple yet effective semantic augmentation module provides self-supervision when learning flow and its boundaries for vehicles, poles, and sky. Together, these injections of semantic information improve the KITTI-2015 optical flow test error rate from 11.80% to 8.38%. We also show visible improvements around object boundaries as well as a greater ability to generalize across datasets. Code will be made available.

翻译：无监督光流估计在遮挡区域、运动边界及低纹理区域尤为困难。研究表明，语义信息与领域知识等额外信息有助于更好地约束该问题。我们提出SemARFlow——一种专为自动驾驶数据设计的无监督光流网络，该网络将估计的语义分割掩码作为额外输入。这些额外信息被注入编码器及可精细化光流输出的学习型上采样模块。此外，一种简单而有效的语义增强模块可为车辆、杆状物及天空等目标的光流及其边界学习提供自监督信号。通过上述语义信息注入，KITTI-2015光流测试基准的错误率从11.80%降至8.38%。我们还在目标边界附近观察到显著改进，并展现出更强的跨数据集泛化能力。代码将开源。