论文标题
RAFT-MSF：使用复发优化器的自我监督的单眼场景流
RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizer
论文作者
论文摘要
从单眼摄像机流动的学习场景仍然是一项具有挑战性的任务，因为它的不适以及缺乏带注释的数据。自我监督的方法证明了从未标记的数据中的学习场景流量估计，但它们的准确性滞后于（半）监督方法。在本文中，我们介绍了一种自我监管的单眼场景流量方法，该方法可大大提高以前方法的准确性。基于RAFT（一种最新的光流模型），我们设计了一个新的解码器，以同时更新3D运动场和差异图。此外，我们提出了一个增强的上采样层和差异初始化技术，总体上将准确性提高到7.2％。我们的方法在所有自我监督的单眼流程方法中实现了最新的准确性，将精度提高了34.2％。我们的微调模型优于最佳的前一个半监督方法，运行时间更快。代码将公开可用。
Learning scene flow from a monocular camera still remains a challenging task due to its ill-posedness as well as lack of annotated data. Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their accuracy lags behind (semi-)supervised methods. In this paper, we introduce a self-supervised monocular scene flow method that substantially improves the accuracy over the previous approaches. Based on RAFT, a state-of-the-art optical flow model, we design a new decoder to iteratively update 3D motion fields and disparity maps simultaneously. Furthermore, we propose an enhanced upsampling layer and a disparity initialization technique, which overall further improves accuracy up to 7.2%. Our method achieves state-of-the-art accuracy among all self-supervised monocular scene flow methods, improving accuracy by 34.2%. Our fine-tuned model outperforms the best previous semi-supervised method with 228 times faster runtime. Code will be publicly available.
