Work

Domain-size pooling in local descriptors: DSP-SIFT

Year: 2015
Type: conference-paper
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.
Language: English
Open Access status: green
OpenAlex ID: W1901447884
FWCI: 8.166
Cites: 52
Cited by: 187
Related to: 10