基于子流形稀疏卷积的高效邻域一致性网络
Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
摘要：
在这项工作中，我们的目标是准确估计一对图像之间的局部对应关系的问题。我们采用了最近的邻里共识网络，已经证明了有前途的性能困难的对应问题，并提出修改，以克服其主要局限性：大内存消耗，大的推理时间和本地化差的对应。我们提出的修改可以减少内存占用和执行时间比$10\times$，具有相同的结果。这是通过稀疏化包含试探性匹配的相关张量，以及使用子流形稀疏卷积的4D CNN的后续处理来实现的。通过以更高的分辨率处理输入图像（这是可能的，因为减少了存储器占用）和通过新颖的两阶段对应重新定位模块，显著提高了定位精度。所提出的稀疏-NCNet方法在HPatches序列和InLoc视觉定位基准测试中获得了最先进的结果，并在亚琛昼夜基准测试中获得了有竞争力的结果。
英文摘要：
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.
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。
