arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.00833cs.CV
收藏

重新思考RAFT以实现高效光流估计

Rethinking RAFT for Efficient Optical Flow

Sharif University of Technology(谢里夫理工大学)

Navid Eslami, Farnoosh Arefi, Amir M. Mansourian, Shohreh Kasaei

AI总结:

本文提出基于RAFT框架的高效光流估计方法Ef-RAFT,通过引入注意力特征定位(AFL)和无定形查找算子(ALO)解决大位移和重复模式问题,在Sintel和KITTI数据集上分别提升10%和5%,同时显著降低内存消耗和运行时间。

摘要:

尽管基于深度学习的光流方法取得了显著进展,但准确估计大位移和重复模式仍然是一个挑战。这些算法中使用的局部特征和相似性搜索模式的局限性导致了这一问题。此外,一些现有方法存在运行缓慢和图形内存消耗过多的问题。为了解决这些问题,本文提出了一种基于RAFT框架的新方法。所提出的基于注意力的特征定位(AFL)方法结合了注意力机制来处理全局特征提取并解决重复模式问题。它引入了一个算子,用于将像素与第二帧中的对应像素进行匹配,并分配准确的流值。此外,提出了一种无定形查找算子(ALO),通过减少其搜索算子中的数据冗余并扩大相似性提取的搜索空间,来提高收敛速度并改善RAFT处理大位移的能力。所提出的方法Efficient RAFT(Ef-RAFT)在Sintel数据集上比RAFT提高了10%,在KITTI数据集上提高了5%。值得注意的是,这些改进是在速度降低33%和内存使用增加仅13%的情况下实现的。代码可在以下网址获取:https://github.com/n3slami/Ef-RAFT

英文摘要:

Despite significant progress in deep learning-based optical flow methods, accurately estimating large displacements and repetitive patterns remains a challenge. The limitations of local features and similarity search patterns used in these algorithms contribute to this issue. Additionally, some existing methods suffer from slow runtime and excessive graphic memory consumption. To address these problems, this paper proposes a novel approach based on the RAFT framework. The proposed Attention-based Feature Localization (AFL) approach incorporates the attention mechanism to handle global feature extraction and address repetitive patterns. It introduces an operator for matching pixels with corresponding counterparts in the second frame and assigning accurate flow values. Furthermore, an Amorphous Lookup Operator (ALO) is proposed to enhance convergence speed and improve RAFTs ability to handle large displacements by reducing data redundancy in its search operator and expanding the search space for similarity extraction. The proposed method, Efficient RAFT (Ef-RAFT),achieves significant improvements of 10% on the Sintel dataset and 5% on the KITTI dataset over RAFT. Remarkably, these enhancements are attained with a modest 33% reduction in speed and a mere 13% increase in memory usage. The code is available at: https://github.com/n3slami/Ef-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。

↑