Improved Descriptors for Patch Matching and Reconstruction

Mitra, Rahul; Zhang, Jiakai; Narayan, Sanath; Ahmed, Shuaib; Chandran, Sharat; Jain, Arjun

doi:10.1109/iccvw.2017.125

Cited by 3 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By subtracting the values from the circular field within the pixel block, centred around the central value, from the central pixel value, the difference vector d p is obtained. Subsequently, this vector can be decomposed into the symbol vector [0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1] and the absolute value vector [70,133,23,11,48,125,121,78,32,31,113,108,57,80,69,12].…”

Section: Lmfd Feature Point Detection and Matrix Decompositionmentioning

confidence: 99%

LMFD: lightweight multi-feature descriptors for image stitching

Fan,

Mao,

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Image stitching is a fundamental pillar of computer vision, and its effectiveness hinges significantly on the quality of the feature descriptors. However, the existing feature descriptors face several challenges, including inadequate robustness to noise or rotational transformations and limited adaptability during hardware deployment. To address these limitations, this paper proposes a set of feature descriptors for image stitching named Lightweight Multi-Feature Descriptors (LMFD). Based on the extensive extraction of gradients, means, and global information surrounding the feature points, feature descriptors are generated through various combinations to enhance the image stitching process. This endows the algorithm with formidable rotational invariance and noise resistance, thereby improving its accuracy and reliability. Furthermore, the feature descriptors take the form of binary matrices consisting of 0s and 1s, not only facilitating more efficient hardware deployment but also enhancing computational efficiency. The utilization of binary matrices significantly reduces the computational complexity of the algorithm while preserving its efficacy. To validate the effectiveness of LMFD, rigorous experimentation was conducted on the Hpatches and 2D-HeLa datasets. The results demonstrate that LMFD outperforms state-of-the-art image matching algorithms in terms of accuracy. This empirical evidence solidifies the superiority of LMFD and substantiates its potential for practical applications in various domains.

show abstract

Section: Lmfd Feature Point Detection and Matrix Decompositionmentioning

confidence: 99%

LMFD: lightweight multi-feature descriptors for image stitching

Fan,

Mao,

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…It is also possible to learn image descriptors, and this approach can improve performance beyond that of hand-crafted descriptors (Brown et al, 2011;Schönberger et al, 2017;Simonyan et al, 2014;Trzcinski et al, 2012). Recently, learning image descriptors using deep neural networks has become a popular approach (Balntas et al, 2017a(Balntas et al, , 2016(Balntas et al, , 2018Kwang et al, 2016;Mitra et al, 2017;Simo-Serra et al, 2015;Komodakis, 2015, 2017).…”

Section: Related Workmentioning

confidence: 99%

Explaining away results in accurate and tolerant template matching

Spratling

2020

Pattern Recognition

View full text Add to dashboard Cite

Recognising and locating image patches or sets of image features is an important task underlying much work in computer vision. Traditionally this has been accomplished using template matching. However, template matching is notoriously brittle in the face of changes in appearance caused by, for example, variations in viewpoint, partial occlusion, and non-rigid deformations. This article tests a method of template matching that is more tolerant to such changes in appearance and that can, therefore, more accurately identify image patches. In traditional template matching the comparison between a template and the image is independent of the other templates. In contrast, the method advocated here takes into account the evidence provided by the image for the template at each location and the full range of alternative explanations represented by the same template at other locations and by other templates. Specifically, the proposed method of template matching is performed using a form of probabilistic inference known as "explaining away". The algorithm used to implement explaining away has previously been used to simulate several neurobiological mechanisms, and been applied to image contour detection and pattern recognition tasks. Here is is applied for the first time to image patch matching, and is shown to produce superior results in comparison to the current state-of-the-art methods.

show abstract

“…Descriptors can also be extracted at multiple scales of a Gaussian pyramid to capture multi-scale information of an interest point [11][12] [46]. Coarser levels allow one to distinguish locally repeated patterns, whereas finer levels capture subtle changes thus helping to discriminate nearby points [36]. The Scale-less SIFT (SLS) descriptor [46] approximates SIFT descriptors [2] sampled at multiple scales with a linear subspace.…”

Section: A On Handling Scale Variationsmentioning

confidence: 99%

“…Patch-based CNN features learn to discriminate correct and incorrect matches with supervised training. Examples include DeepDesc [33], DeepCompare [34], TFeat [35], and Multiresolution CNN (MR-CNN) [36]. DeepDesc [33] and Deep-Compare [34] train a Siamese network with pairs of annotated patches to push away incorrect patches and to move corresponding patches closer on a Euclidean, Hamming, or learnt metric.…”

Section: Introductionmentioning

confidence: 99%

“…To reduce overfitting, TFeat [35] extends this network to triplets (anchor, positive sample, negative sample) and uses hard negative mining by swapping anchor and positive samples. To improve scale invariance, MR-CNN [36] learns a descriptor using image patches scaled at three resolutions as input to a three-stream Siamese network. However, TFeat outperforms MR-CNN in patch and image matching as well as in efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Spatio-Temporal Multi-Scale Binary Descriptor

Xompero

Lanz

Cavallaro

2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Binary descriptors are widely used for multi-view matching and robotic navigation. However, their matching performance decreases considerably under severe scale and viewpoint changes in non-planar scenes. To overcome this problem, we propose to encode the varying appearance of selected 3D scene points tracked by a moving camera with compact spatio-temporal descriptors. To this end, we first track interest points and capture their temporal variations at multiple scales. Then, we validate feature tracks through 3D reconstruction and compress the temporal sequence of descriptors by encoding the most frequent and stable binary values. Finally, we determine multiscale correspondences across views with a matching strategy that handles severe scale differences. The proposed spatio-temporal multi-scale approach is generic and can be used with a variety of binary descriptors. We show the effectiveness of the joint multiscale extraction and temporal reduction through comparisons of different temporal reduction strategies and the application to several binary descriptors.

show abstract

Improved Descriptors for Patch Matching and Reconstruction

Cited by 3 publications

References 23 publications

LMFD: lightweight multi-feature descriptors for image stitching

LMFD: lightweight multi-feature descriptors for image stitching

Explaining away results in accurate and tolerant template matching

A Spatio-Temporal Multi-Scale Binary Descriptor

Contact Info

Product

Resources

About