Multi-Image Semantic Matching by Mining Consistent Features
arXiv:1711.07641
Abstract
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.
arXiv commentCVPR 2018
References in corpus (10)
- Universal Correspondence Network
- Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT
- A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting
- LIFT: Learned Invariant Feature Transform
- Near-Optimal Joint Object Matching via Convex Relaxation
- WarpNet: Weakly Supervised Matching for Single-view Reconstruction
- Learning Dense Correspondence via 3D-guided Cycle Consistency
- Learning Covariant Feature Detectors
- Multi-Image Matching via Fast Alternating Minimization
- Virtual View Networks for Object Reconstruction