论文标题
自我调整：立体声序列中的自我监视场景流程预测
Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences
论文作者
论文摘要
近年来，深度神经网络表明了它们在解决包括场景流预测在内的许多计算机视觉任务方面的超出能力。但是，大多数进步取决于每个像素地面真相注释的大量致密性，这对于现实生活中的情况很难获得。因此，通常依靠合成数据进行监督，从而导致培训和测试数据之间的表示差距。即使有大量未标记的现实世界数据可用，但对于场景流预测的自我监督方法仍然存在很大的缺乏。因此，我们探讨了基于人口普查转换和遮挡意识到的双向位移的自我监督损失的扩展，以解决场景流动预测问题。关于Kitti场景流基准，我们的方法的表现优于同一网络的相应监督预培训，并显示出改善的概括功能，同时达到了更快的收敛速度。
In recent years, deep neural networks showed their exceeding capabilities in addressing many computer vision tasks including scene flow prediction. However, most of the advances are dependent on the availability of a vast amount of dense per pixel ground truth annotations, which are very difficult to obtain for real life scenarios. Therefore, synthetic data is often relied upon for supervision, resulting in a representation gap between the training and test data. Even though a great quantity of unlabeled real world data is available, there is a huge lack in self-supervised methods for scene flow prediction. Hence, we explore the extension of a self-supervised loss based on the Census transform and occlusion-aware bidirectional displacements for the problem of scene flow prediction. Regarding the KITTI scene flow benchmark, our method outperforms the corresponding supervised pre-training of the same network and shows improved generalization capabilities while achieving much faster convergence.
