Multi-Image Semantic Matching by Mining Consistent Features
This addresses the challenge of scalable multi-image matching for computer vision applications, though it appears incremental as it builds on existing methods with specific optimizations.
The paper tackles the problem of estimating semantic correspondences across multiple images by identifying and matching only a sparse set of reliable features, which improves scalability to thousands of images and achieves competitive performance on benchmarks.
This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a sparse set of reliable features in the image collection. In this way, the proposed method is able to prune nonrepeatable features and also highly scalable to handle thousands of images. We additionally propose a low-rank constraint to ensure the geometric consistency of feature correspondences over the whole image collection. Besides the competitive performance on multi-graph matching and semantic flow benchmarks, we also demonstrate the applicability of the proposed method for reconstructing object-class models and discovering object-class landmarks from images without using any annotation.