论文标题
高分辨率多尺度筏（强大的视觉挑战2022）
High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)
论文作者
论文摘要
在本报告中，我们介绍了赢得了强大的视觉挑战2022的光流方法MS-RAFT+。它基于MS-RAFT方法，该方法成功地将多个多规模概念集成到单尺度筏中。我们的方法通过利用额外的量表来估计流量来扩展这种方法，这是通过按需计算可行的。这样，它不仅可以在原始分辨率的一半中运行，还可以使用MS-RAFT的共享凸UPS采样器来获得完整的分辨率流。此外，我们的方法依赖于培训期间的调整调整计划。反过来，这旨在改善跨基准的概括。在强大的视觉挑战中的所有参与方法中，我们的方法在毒蛇上排名第一，在Kitti，Sintel和Middlebury上排名第二，这是整体排名的第一名。
In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during training. This in turn aims at improving the generalization across benchmarks. Among all participating methods in the Robust Vision Challenge, our approach ranks first on VIPER and second on KITTI, Sintel, and Middlebury, resulting in the first place of the overall ranking.
