We introduce a simple modification of local image descriptors, such as SIFT, based on pooling gradient orientations across different domain sizes, in addition to spatial locations. The resulting descriptor, which we call DSP-SIFT, outperforms other methods in wide-baseline matching benchmarks, including those based on convolutional neural networks, despite having the same dimension of SIFT and requiring no training.
@article{arxiv.1412.8556,
title = {Domain-Size Pooling in Local Descriptors: DSP-SIFT},
author = {Jingming Dong and Stefano Soatto},
journal= {arXiv preprint arXiv:1412.8556},
year = {2015}
}
Comments
Extended version of the CVPR 2015 paper. Technical Report UCLA CSD 140022