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 is available at https://github.com/duke-vision/semantic-unsup-flow-release.

翻译：无监督光流估计在遮挡区域、运动边界附近以及低纹理区域中尤为困难。我们证明，语义信息与领域知识等附加信息能够有效约束该问题。本文提出SemARFlow——一种专为自动驾驶数据设计的无监督光流网络，该网络将预估的语义分割掩模作为额外输入。这些附加信息被注入编码器及一个学习型上采样模块中，该模块用于优化光流输出。此外，一个简洁高效的语义增强模块可在学习车辆、杆状物及天空等目标的光流及其边界时提供自监督信号。通过注入语义信息，KITTI-2015光流测试错误率从11.80%降至8.38%。实验还表明，该方法在物体边界处可见效果提升，并增强了跨数据集的泛化能力。代码已开源：https://github.com/duke-vision/semantic-unsup-flow-release。