Keypoints from symmetries by wave propagation

Salti, Samuele; Lanza, Alessandro; Stefano, Luigi Di

doi:10.1109/cvpr.2013.373

Cited by 36 publications

(27 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SURF [3] approximates LoG use a box filter and significantly speeds up the detection. Other popular hand-crafted features include WADE [21], Edge Foci [34], Harris corners [7] and its affine-covariant [16].…”

Section: Related Workmentioning

confidence: 99%

RF-Net: An End-To-End Image Matching Network Based on Receptive Field

Shen

Wang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images. Building end-toend trainable matching framework is desirable and challenging. The very recent approach, LF-Net, successfully embeds the entire feature extraction pipeline into a jointly trainable pipeline, and produces the state-of-the-art matching results. This paper introduces two modifications to the structure of LF-Net. First, we propose to construct receptive feature maps, which lead to more effective keypoint detection. Second, we introduce a general loss function term, neighbor mask, to facilitate training patch selection. This results in improved stability in descriptor training. We trained RF-Net on the open dataset HPatches, and compared it with other methods on multiple benchmark datasets. Experiments show that RF-Net outperforms existing state-of-the-art methods. * Corresponding author.to make them optimally cooperate with each other, hence, is more desirable. However, training such a network is difficult because the two subcomponents have their individually different objectives to optimize. Not many successful end-to-end matching pipelines have been reported in literatures. LIFT [29] is probably the first notable design towards this goal. However, LIFT relies on the output of SIFT detector to initialize the training, and hence, its detector behaves similarly to the SIFT detector. The recent network, SuperPoint [5], achieves this end-to-end training. But its detector needs to be pre-trained on synthetic image sets, and whole network is trained using images under synthesized affine transformations. The more recent LF-Net [18] is inspired by Q-learning, and uses a Siamese architecture to train the entire network without the help of any hand-craft method. In this paper, we develop an end-to-end matching network with enhanced detector and descriptor training modules, which we elaborate as follows. Feature Maps shared 5 × 5

show abstract

Section: Related Workmentioning

confidence: 99%

RF-Net: An End-To-End Image Matching Network Based on Receptive Field

Shen

Wang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Some typical examples of the detectors of this type are Harris corners [4] for corner detection, SIFT [5], SURF [6], MSER [7] for blob detection, and SFOP [8] for junction detection. Besides the list of the aforementioned detectors, there are a vast number of detectors such as SIFER [11], D-SIFER [12], WADE [13], Edge Foci [2] targeting detection of different structures with various customizations. Although current detectors rely on some more or less different pre-designed structures, the structures share a common factor in that they have some levels of complexity.…”

Section: Hand-crafted Feature Detectormentioning

confidence: 99%

SCK: A Sparse Coding Based Key-Point Detector

Hong-Phuoc

Guan

2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

All current popular hand-crafted key-point detectors such as Harris corner, MSER, SIFT, SURF… rely on some specific pre-designed structures for the detection of corners, blobs, or junctions in an image. In this paper, a novel sparse coding based key-point detector which requires no particular predesigned structures is presented. The key-point detector is based on measuring the complexity level of each block in an image to decide where a key-point should be. The complexity level of a block is defined as the total number of non-zero components of a sparse representation of that block. Generally, a block constructed with more components is more complex and has greater potential to be a good keypoint. Experimental results on Webcam and EF datasets [1,2] show that the proposed detector achieves significantly high repeatability compared to hand-crafted features, and even outperforms the matching scores of the state-of-the-art learning based detector.

show abstract

“…Detectors evaluation. The following detectors are compared: MSER [22], DoG [21], Hessian-Affine [24] (implementation [31]), FOCI [45], IIDOG [42], WADE [34], WαSH [41], SURF [7], SFOP [12], AKAZE [5]. We focus on getting a reliable answer to the "match/non-match" question in real image pairs.…”

Section: Evaluation Of Description and Detection Algorithmsmentioning

confidence: 99%

WxBS: Wide Baseline Stereo Generalizations

Mishkin¹,

Matas²,

Perdoch

et al. 2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

We present a generalization of the wide baseline two view matching problem -WXBS, where X stands for a different subset of "wide baselines" in acquisition conditions such as geometry, illumination, sensor and appearance. We introduce a novel dataset of groundtruthed image pairs which include multiple "wide baselines" and show that state-of-theart matchers fail on almost all image pairs from the set. A novel matching algorithm for addressing the WXBS problem is introduced and we show experimentally that the WXBS-M matcher dominates the state-of-the-art methods both on the new and existing datasets.

show abstract

Keypoints from symmetries by wave propagation

Cited by 36 publications

References 24 publications

RF-Net: An End-To-End Image Matching Network Based on Receptive Field

RF-Net: An End-To-End Image Matching Network Based on Receptive Field

SCK: A Sparse Coding Based Key-Point Detector

WxBS: Wide Baseline Stereo Generalizations

Contact Info

Product

Resources

About