In the era of end-to-end deep learning, many advances in computer vision are driven by large amounts of labeled data. In the optical flow setting, however, obtaining dense per-pixel ground truth for real scenes is difficult and thus such data is rare. Therefore, recent end-to-end convolutional networks for optical flow rely on synthetic datasets for supervision, but the domain mismatch between training and test scenarios continues to be a challenge. Inspired by classical energy-based optical flow methods, we design an unsupervised loss based on occlusion-aware bidirectional flow estimation and the robust census transform to circumvent the need for ground truth flow. On the KITTI benchmarks, our unsupervised approach outperforms previous unsupervised deep networks by a large margin, and is even more accurate than similar supervised methods trained on synthetic datasets alone. By optionally fine-tuning on the KITTI training data, our method achieves competitive optical flow accuracy on the KITTI 2012 and 2015 benchmarks, thus in addition enabling generic pre-training of supervised networks for datasets with limited amounts of ground truth.

本研究提出一种利用基于能量的方法进行光流估计的无监督学习方法以替代对真实场景难以获得的像素精确度地面实况数据的依赖，此方法在KITTI基准测试中的表现优于以往的无监督深度网络，甚至比仅在合成数据集上进行训练的类似监督方法更准确，在KITTI 2012和2015基准测试中具有竞争优势。

UnFlow: 双向Census损失的光流无监督学习