English

Domain-Size Pooling in Local Descriptors: DSP-SIFT

Computer Vision and Pattern Recognition 2015-05-06 v3

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-22T07:46:40.321Z