论文标题
通过Submanifold稀疏卷积的有效邻里共识网络
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
论文作者
论文摘要
在这项工作中，我们针对估计一对图像之间准确局部对应关系的问题。我们采用了最近的社区共识网络，这些网络表现出了难以克服其主要局限性的艰难对应问题的有希望的表现：大量的记忆消耗，较大的推理时间和局部局部对应关系不佳。我们提出的修改可以减少内存足迹和执行时间超过$ 10 \ times $，结果等效。这是通过稀疏包含暂定匹配的相关张量来实现的，并使用Submanifold稀疏卷积使用4D CNN进行处理。通过在较高分辨率中处理输入图像，可以显着提高定位精度，这是由于记忆足迹的降低以及新型的两阶段对应重新定位模块所致。提出的稀疏-NCNET方法在HPATCHES序列和INLOC视觉定位基准中获得了最新的结果，并在亚洲昼夜基准中获得了竞争性结果。
In this work we target the problem of estimating accurately localised correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence problems and propose modifications to overcome their main limitations: large memory consumption, large inference time and poorly localised correspondences. Our proposed modifications can reduce the memory footprint and execution time more than $10\times$, with equivalent results. This is achieved by sparsifying the correlation tensor containing tentative matches, and its subsequent processing with a 4D CNN using submanifold sparse convolutions. Localisation accuracy is significantly improved by processing the input images in higher resolution, which is possible due to the reduced memory footprint, and by a novel two-stage correspondence relocalisation module. The proposed Sparse-NCNet method obtains state-of-the-art results on the HPatches Sequences and InLoc visual localisation benchmarks, and competitive results in the Aachen Day-Night benchmark.
