On SIFTs and their scales

  title={On SIFTs and their scales},
  author={Tal Hassner and Viki Mayzels and Lihi Zelnik-Manor},
  journal={2012 IEEE Conference on Computer Vision and Pattern Recognition},
Scale invariant feature detectors often find stable scales in only a few image pixels. Consequently, methods for feature matching typically choose one of two extreme options: matching a sparse set of scale invariant features, or dense matching using arbitrary scales. In this paper we turn our attention to the overwhelming majority of pixels, those where stable scales are not found by standard techniques. We ask, is scale-selection necessary for these pixels, when dense, scale-invariant matching… 

Figures and Tables from this paper

SIFTing Through Scales

This paper turns to the overwhelming majority of pixels, those where stable scales are not found by standard techniques, and shows that representing each pixel as a set of SIFTs, extracted at multiple scales, allows for far better matches than single-scale descriptors, but at a computational price.

Dense, Scale-Less Descriptors

This chapter discusses alternative representations designed to capture multiscale appearance, even in image regions where existing methods for scale selection are not effective, and demonstrates how the use of the SLS descriptor can act as an alternative to existing, single scale representations, allowing for accurate dense correspondences between images with scale-varying content.

Dense Correspondences across Scenes and Scales

  • Moria TauTal Hassner
  • Environmental Science, Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
It is shown that scales estimated in sparse interest points may be propagated to neighboring pixels where this information cannot be reliably determined, which allows scale invariant descriptors to be extracted anywhere in the image.

Dense Scale Invariant Descriptors for Images and Surfaces

This work constructs scale-invariant signal descriptors by introducing a method that does not rely on scale selection and relies on a combination of logarithmic sampling with multi-scale signal processing that turns scaling in the original signal domain into a translation in a new domain.

Scale propagation for Accurate and Practical Dense Correspondence Estimation Across Scenes and Scales

  • Environmental Science, Computer Science
  • 2014
It is shown that scales estimated in sparse interest points may be propagated to neighboring pixels where this information cannot be reliably determined, which allows scale invariant descriptors to be extracted anywhere in the image.

Scale Selection in SIFT Flow for Robust Dense Image Matching

It is shown that by applying ORSF and OMS, the accuracy of SIFT flow for dense image matching is greatly improved on images with significant scale changes, and two new concepts, namely, the optimal relative scale factor (ORSF) and the optimal matching scale (OMS) using gradient-enhanced normalized mutual information are proposed.

Scale-Space SIFT flow

This paper proposes a simple, intuitive, and very effective approach, Scale-Space SIFT flow, to deal with the large scale differences in different image locations, and introduces a scale field to the SIFTflow function to automatically explore the scale deformations.

Enhancing low-level features with mid-level cues

An approach to dense stereo reconstruction with spatiotemporal features, which unlike existing works remains applicable to wide baselines, and a technique to exploit segmentation cues to construct dense descriptors invariant to background variability, such as occlusions or background motion.

Anatomy of the SIFT Method

This analysis demonstrates that, despite the fact that numerous methods claim to outperform the SIFT method, there is in fact limited room for improvement in methods that extract keypoints from a scale-space.

Unsupervised Feature Learning for Dense Correspondences Across Scenes

A fast, accurate matching method for estimating dense pixel correspondences across scenes that learns features from a large amount of unlabeled image patches using unsupervised learning, and is seamlessly embedded into a multi-layer matching framework.



Scale invariance without scale selection

This work constructs scale invariant descriptors (SIDs) without requiring the estimation of image scale and shows that the constructed SIDs outperform state-of-the-art descriptors on standard datasets and the performance of a boundary-based model is systematically improved on an object detection task.

Is SIFT scale invariant

This note is devoted to a mathematical exploration of whether Lowe's Scale-Invariant Feature Transform (SIFT)[21], a very successful image matching method, is similarity invariant as claimed. It is

Speeded-Up Robust Features (SURF)

A performance evaluation of local descriptors

It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.

DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo

An EM-based algorithm to compute dense depth and occlusion maps from wide-baseline image pairs using a local image descriptor, DAISY, which is very efficient to compute densely and robust against many photometric and geometric transformations.

Scale & Affine Invariant Interest Point Detectors

A comparative evaluation of different detectors is presented and it is shown that the proposed approach for detecting interest points invariant to scale and affine transformations provides better results than existing methods.

SIFT Flow: Dense Correspondence across Different Scenes

A method to align an image to its neighbors in a large image collection consisting of a variety of scenes, and applies the SIFT flow algorithm to two applications: motion field prediction from a single static image and motion synthesis via transfer of moving objects.

Sampling Strategies for Bag-of-Features Image Classification

It is shown experimentally that for a representative selection of commonly used test databases and for moderate to large numbers of samples, random sampling gives equal or better classifiers than the sophisticated multiscale interest operators that are in common use.

Feature Detection with Automatic Scale Selection

  • T. Lindeberg
  • Computer Science
    International Journal of Computer Vision
  • 2004
It is shown how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation and how it can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure.

SIFT Flow: Dense Correspondence across Scenes and Its Applications

SIFT flow is proposed, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence.