arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.00330cs.CV
收藏

DIP:高分辨率光流的深度逆块匹配

DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

Megvii(旷视科技);Tencent(腾讯)

Zihua Zheng, Ni Nie, Zhi Ling, Pengfei Xiong, Jiangyu Liu, Hao Wang, Jiankun Li

摘要:

最近,密集相关体方法在光流中实现了最先进的性能。然而,相关体积计算需要大量的存储器,这使得在高分辨率图像上的预测变得困难。在本文中,我们提出了一种新的基于Patchmatch的框架工作的高分辨率光流估计。具体来说,我们介绍了第一个基于端到端Patchmatch的深度学习光流。该算法利用Patchmatch的传播和局部搜索机制,以较少的内存获得高精度的结果。此外,提出了一种新的逆传播算法,将复杂的传播运算解耦,从而大大减少了多次迭代的计算量。在提交时,我们的方法在流行的KITTI 2015基准测试的所有指标中排名第一,在已发布的光流方法中,在Sintel清洁基准测试的EPE中排名第二。实验表明,该方法具有较强的跨数据集泛化能力,F1-all达到13.73%,比KITTI 2015上发表的最佳结果17.4%降低了21%。更重要的是,我们的方法在高分辨率数据集DAVIS上显示了良好的细节保持效果,并且比RAFT少消耗2倍的内存。

英文摘要:

Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow. However, the correlation volume computation requires a lot of memory, which makes prediction difficult on high-resolution images. In this paper, we propose a novel Patchmatch-based framework to work on high-resolution optical flow estimation. Specifically, we introduce the first end-to-end Patchmatch based deep learning optical flow. It can get high-precision results with lower memory benefiting from propagation and local search of Patchmatch. Furthermore, a new inverse propagation is proposed to decouple the complex operations of propagation, which can significantly reduce calculations in multiple iterations. At the time of submission, our method ranks first on all the metrics on the popular KITTI2015 benchmark, and ranks second on EPE on the Sintel clean benchmark among published optical flow methods. Experiment shows our method has a strong cross-dataset generalization ability that the F1-all achieves 13.73%, reducing 21% from the best published result 17.4% on KITTI2015. What's more, our method shows a good details preserving result on the high-resolution dataset DAVIS and consumes 2x less memory than RAFT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑