Journal
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 685-694Publisher
IEEE
DOI: 10.1109/CVPR.2018.00078
Keywords
-
Categories
Funding
- ARL MAST-CTA [W911NF-08-2-0004]
- ARL RCTA [W911NF-10-2-0016]
- ONR [N00014-17-1-2093]
- Fundamental Research Funds for the Central Universities [2018FZA5011]
Ask authors/readers for more resources
This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pair wise 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available