WxBS: Wide Baseline Stereo Generalizations

Mishkin, Dmytro; Matas, Jiřı́; Perdoch, Michal; Lenc, Karel

doi:10.5244/c.29.12

Cited by 50 publications

(49 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Edge Foci dataset [42] consists of sequences with very strong changes in viewing conditions, making the evaluation somewhat specialized to extreme cases; furthermore, the groundtruth for non-planar scenes does not uniquely identify the correspondences since the transformations cannot be approximated well by homographies. Similarly, the WxBs dataset [25] focuses on very wide baseline matching, with extreme changes in geometry, illumination, and appearance over time.…”

Section: Image-based Benchmarksmentioning

confidence: 99%

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

Balntas

Lenc

Vedaldi

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

115

View full text Add to dashboard Cite

In this paper, we propose a novel benchmark for evaluating local image descriptors. We demonstrate that the existing datasets and evaluation protocols do not specify unambiguously all aspects of evaluation, leading to ambiguities and inconsistencies in results reported in the literature. Furthermore, these datasets are nearly saturated due to the recent improvements in local descriptors obtained by learning them from large annotated datasets. Therefore, we introduce a new large dataset suitable for training and testing modern descriptors, together with strictly defined evaluation protocols in several tasks such as matching, retrieval and classification. This allows for more realistic, and thus more reliable comparisons in different application scenarios. We evaluate the performance of several state-of-theart descriptors and analyse their properties. We show that a simple normalisation of traditional hand-crafted descriptors can boost their performance to the level of deep learning based descriptors within a realistic benchmarks evaluation.

show abstract

Section: Image-based Benchmarksmentioning

confidence: 99%

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

Balntas

Lenc

Vedaldi

et al. 2019

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

115

View full text Add to dashboard Cite

show abstract

“…Finally, a particularly challenging case in image interest point detection is the cross-modal one: the interest points should be repeatable among different image modalities. Several works mention this complex issue ( [27], [2], [13], [23]) but do not propose a general solution. Our approach, on the contrary, is general in a sense that the same learning procedure could be applied to different tasks: we show it to work for RGB/RGB and RGB/depth modality pairs.…”

Section: Related Workmentioning

confidence: 99%

Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection

Savinov¹,

Seki

Ladický³

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

172

120

View full text Add to dashboard Cite

Several machine learning tasks require to represent the data using only a sparse set of interest points. An ideal detector is able to find the corresponding interest points even if the data undergo a transformation typical for a given domain. Since the task is of high practical interest in computer vision, many hand-crafted solutions were proposed. In this paper, we ask a fundamental question: can we learn such detectors from scratch? Since it is often unclear what points are "interesting", human labelling cannot be used to find a truly unbiased solution. Therefore, the task requires an unsupervised formulation. We are the first to propose such a formulation: training a neural network to rank points in a transformation-invariant manner. Interest points are then extracted from the top/bottom quantiles of this ranking. We validate our approach on two tasks: standard RGB image interest point detection and challenging cross-modal interest point detection between RGB and depth images. We quantitatively show that our unsupervised method performs better or on-par with baselines.

show abstract

“…Pixel p is shown with "×". P: polar parametrization, C: cartesian parametrization, W UA is shown for t = 0.7 and W US for β = λ 40 . Whitening is learned on Liberty dataset.…”

Section: Combining Kernel Descriptorsmentioning

confidence: 99%

“…Despite the large focus on Convolutional Neural Networks (CNN) to process whole images, local features A. Mukundan [22,25,51], stereo matching [40], or retrieval under severe change in viewpoint or scale [53,72].…”

Section: Introductionmentioning

confidence: 99%

Understanding and Improving Kernel Local Descriptors

et al. 2018

View full text Add to dashboard Cite

We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch mis-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Combined with whitening of the descriptor space, that is learned with or without supervision, the performance is significantly improved. We analyze the effect of the whitening on patch similarity and demonstrate its semantic meaning. Our unsupervised variant is the best performing descriptor constructed without the need of labeled data. Despite the simplicity of the proposed descriptor, it competes well with deep learning approaches on a number of different tasks.

show abstract

WxBS: Wide Baseline Stereo Generalizations

Cited by 50 publications

References 44 publications

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection

Understanding and Improving Kernel Local Descriptors

Contact Info

Product

Resources

About