Scale-Space SIFT flow

@article{Qiu2014ScaleSpaceSF,
  title={Scale-Space SIFT flow},
  author={Weichao Qiu and Xinggang Wang and Xiang Bai and Alan Loddon Yuille and Zhuowen Tu},
  journal={IEEE Winter Conference on Applications of Computer Vision},
  year={2014},
  pages={1112-1119}
}
The state-of-the-art SIFT flow has been widely adopted for the general image matching task, especially in dealing with image pairs from similar scenes but with different object configurations. However, the way in which the dense SIFT features are computed at a fixed scale in the SIFT flow method limits its capability of dealing with scenes of large scale changes. In this paper, we propose a simple, intuitive, and very effective approach, Scale-Space SIFT flow, to deal with the large scale… 
View on IEEE
cs.jhu.edu
39 Citations
Highly Influential Citations
8
Background Citations
17
Methods Citations
20

Figures and Tables from this paper

39 Citations

Citation Type

Citation Type

Dense, Scale-Less Descriptors
TLDR
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.
Image Correspondence Using Affine SIFT Flow
TLDR
This work applied SIFT flow algorithm on the affine transformations of images to be aligned to correspond images sharing similar content but vary due to change in acquisition like view angle, scale, and illumination.
Proposal Flow
TLDR
This work introduces a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals, and demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.
SIFTing Through Scales
TLDR
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.
Proposal Flow: Semantic Correspondences from Object Proposals
TLDR
This work introduces a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals, and demonstrates that proposal flow significantly outperforms existing semantic flow methods in various settings.
Dense Correspondences across Scenes and Scales
  • Moria Tau, Tal Hassner
  • Environmental Science, Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
TLDR
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.
Shape-based Image Correspondence
TLDR
This paper investigates the effect of adding shape correspondence constraints either in the form of pair of corresponding contour fragments or pair of closed curves and explores using object proposals as a way of providing shape constraints with encouraging results.
Scale propagation for Accurate and Practical Dense Correspondence Estimation Across Scenes and Scales
  • Environmental Science, Computer Science
  • 2014
TLDR
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.
Improved DSP matching with space-spanning scales and SLIC superpixels for dense scene correspondences
TLDR
This work proposes to use space-spanning scales to improve DSP by extracting dense SIFTs at different scales for different pyramid level and shows that this post-process is very efficient in reducing clutters and preserves much more texture information.
Subpixel Semantic Flow
TLDR
This paper revisits a classic dense descriptor, namely Geometric Blur, which is, in contrast, extracted from a linear filter response that can be linearized and therefore interpolated at subpixel values, and presents promising results encouraging the use of gradient based continuous optimization in establishing dense semantic correspondences.
...
...

References

SHOWING 1-10 OF 31 REFERENCES
SIFT Flow: Dense Correspondence across Different Scenes
TLDR
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.
SIFT Flow: Dense Correspondence across Scenes and Its Applications
TLDR
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.
On SIFTs and their scales
TLDR
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.
DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo
TLDR
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.
Nonparametric Scene Parsing via Label Transfer
TLDR
This paper proposes a novel, nonparametric approach for object recognition and scene parsing using a new technology the authors name label transfer, which is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.
Non-rigid dense correspondence with applications for image enhancement
TLDR
The usefulness of the method is demonstrated using three applications for automatic example-based photograph enhancement: adjusting the tonal characteristics of a source image to match a reference, transferring a known mask to a new image, and kernel estimation for image deblurring.
Deformable Spatial Pyramid Matching for Fast Dense Correspondences
TLDR
This work introduces a fast deformable spatial pyramid (DSP) matching algorithm for computing dense pixel correspondences that simultaneously regularizes match consistency at multiple spatial extents-ranging from an entire image, to coarse grid cells, to every single pixel.
Nonparametric scene parsing: Label transfer via dense scene alignment
TLDR
Compared to existing object recognition approaches that require training for each object category, the proposed nonparametric scene parsing system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.
Scale invariance without scale selection
  • I. Kokkinos, A. Yuille
  • Computer Science
    2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
TLDR
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.
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
  • S. Lazebnik, C. Schmid, J. Ponce
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
TLDR
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories.
...
...