Domain-Size Pooling in Local Descriptors: DSP-SIFT
This addresses the problem of robust image matching for computer vision applications, but it is incremental as it modifies an existing descriptor.
The paper tackled the problem of improving local image descriptors for wide-baseline matching by introducing domain-size pooling in gradient orientations, resulting in DSP-SIFT, which outperformed other methods including CNN-based ones in benchmarks without increasing dimension or requiring training.
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.