Geometric Image Correspondence Verification by Dense Pixel Matching
2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV)(2019)
摘要
This paper addresses the problem of determining dense pixel correspondences between two images and its application to geometric correspondence verification in image retrieval. The main contribution is a geometric correspondence verification approach for re-ranking a shortlist of retrieved database images based on their dense pair-wise matching with the query image at a pixel level. We determine a set of cyclically consistent dense pixel matches between the pair of images and evaluate local similarity of matched pixels using neural network based image descriptors. Final re-ranking is based on a novel similarity function, which fuses the local similarity metric with a global similarity metric and a geometric consistency measure computed for the matched pixels. For dense matching our approach utilizes a modified version of a recently proposed dense geometric correspondence network (DGC-Net), which we also improve by optimizing the architecture. The proposed model and similarity metric compare favourably to the state-of-the-art image retrieval methods. In addition, we apply our method to the problem of long-term visual localization demonstrating promising results and generalization across datasets.
更多查看译文
关键词
geometric image correspondence verification,dense pixel correspondences,retrieved database images,dense pair-wise matching,query image,cyclically consistent dense pixel,image descriptors,similarity function,global similarity metric,geometric consistency measure,dense matching,dense geometric correspondence network,image retrieval,dense pixel matching,geometric correspondence verification,neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要