Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

In this work we target the problem of estimating accurately localized 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 localized 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. localization 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 relocalization module. The proposed Sparse-NCNet method obtains state-of-the-art results on the HPatches Sequences and InLoc visual localization benchmarks, and competitive results on the Aachen Day-Night benchmark.