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 2209.12699cs.CV
收藏

通过注意力级联体积实现精确且高效的立体匹配

Accurate and Efficient Stereo Matching via Attention Concatenation Volume

Huazhong University of Science and Technology(华中科技大学);Nanjing University of Science and Technology(南京理工大学)

Gangwei Xu, Yun Wang, Junda Cheng, Jinhui Tang, Xin Yang

AI总结:

提出注意力级联体积(ACV)及其快速版Fast-ACV,通过生成注意力权重抑制冗余信息,并设计ACVNet和Fast-ACVNet网络,在多个基准上实现高精度与实时立体匹配。

摘要:

立体匹配是许多视觉和机器人应用的基础构建块。信息丰富且简洁的代价体积表示对于实现高精度和高效率的立体匹配至关重要。在本文中,我们提出了一种新颖的代价体积构建方法,名为注意力级联体积(ACV),它从相关性线索生成注意力权重,以抑制冗余信息并增强级联体积中与匹配相关的信息。ACV可以无缝嵌入到大多数立体匹配网络中,由此产生的网络可以使用更轻量级的聚合网络,同时实现更高的精度。我们进一步设计了ACV的快速版本以实现实时性能,名为Fast-ACV,它从低分辨率相关性线索生成高似然视差假设及相应的注意力权重,以显著降低计算和内存成本,同时保持令人满意的精度。我们Fast-ACV的核心思想是体积注意力传播(VAP),它能够从上采样的相关性体积中自动选择准确的相关性值,并将这些准确值传播给具有模糊相关性线索的周围像素。此外,我们分别基于ACV和Fast-ACV设计了高精度网络ACVNet和实时网络Fast-ACVNet,它们在多个基准上实现了最先进的性能(即,在所有已发表的方法中,我们的ACVNet在KITTI 2015和Scene Flow上排名第2,在KITTI 2012和ETH3D上排名第3;我们的Fast-ACVNet在Scene Flow、KITTI 2012和2015上优于几乎所有最先进的实时方法,同时具有更好的泛化能力)。

英文摘要:

Stereo matching is a fundamental building block for many vision and robotics applications. An informative and concise cost volume representation is vital for stereo matching of high accuracy and efficiency. In this paper, we present a novel cost volume construction method, named attention concatenation volume (ACV), which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume. The ACV can be seamlessly embedded into most stereo matching networks, the resulting networks can use a more lightweight aggregation network and meanwhile achieve higher accuracy. We further design a fast version of ACV to enable real-time performance, named Fast-ACV, which generates high likelihood disparity hypotheses and the corresponding attention weights from low-resolution correlation clues to significantly reduce computational and memory cost and meanwhile maintain a satisfactory accuracy. The core idea of our Fast-ACV is volume attention propagation (VAP) which can automatically select accurate correlation values from an upsampled correlation volume and propagate these accurate values to the surroundings pixels with ambiguous correlation clues. Furthermore, we design a highly accurate network ACVNet and a real-time network Fast-ACVNet based on our ACV and Fast-ACV respectively, which achieve the state-of-the-art performance on several benchmarks (i.e., our ACVNet ranks the 2nd on KITTI 2015 and Scene Flow, and the 3rd on KITTI 2012 and ETH3D among all the published methods; our Fast-ACVNet outperforms almost all state-of-the-art real-time methods on Scene Flow, KITTI 2012 and 2015 and meanwhile has better generalization ability)

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。

↑