D2D: Keypoint Extraction with Describe to Detect Approach

Tian, Yanling; Balntas, Vassileios; Ng, Tony; Barroso-Laguna, Axel; Demiris, Yiannis; Mikolajczyk, Krystian

doi:10.1007/978-3-030-69535-4_14

Cited by 47 publications

(32 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By postponing the detection to a later stage, the obtained key points are more stable. Similar to D2D [80], they proposed a relative and an absolute saliency measure of local deep feature maps along the spatial and depth dimensions to define key points. Benbihi et al [81], proposed a detection method DELF, valid for any trained CNN where key points are regarded as the local maxima of a saliency map computed as the feature gradient for the input image.…”

Section: Local Feature Matchingmentioning

confidence: 99%

A Critical Analysis of Image-based Camera Pose Estimation Techniques

Xu¹,

Wang²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR). After decades of progress, camera localization, also called camera pose estimation could compute the 6DoF pose of objects for a camera in a given image, with respect to different images in a sequence or formats. Structure-based localization methods have achieved great success when integrated with image matching or with a coordinate regression stage. Absolute and relative pose regression methods using transfer learning can support end-to-end localisation to directly regress a camera pose but achieve a less accurate performance. Despite the rapid development of multiple branches in this area, a comprehensive, in-depth and comparative analysis is lacking to summarise, classify and compare, structure-based and regression-based camera localization methods. Existing surveys either focus on larger SLAM (Simultaneous Localization and Mapping) systems or on only part of the camera localization method, lack detailed comparisons and descriptions of the methods or datasets used, neural network designs such as loss designs, and input formats, etc. In this survey, we first introduce specific application areas and the evaluation metrics for camera localization pose according to different sub-

show abstract

Section: Local Feature Matchingmentioning

confidence: 99%

A Critical Analysis of Image-based Camera Pose Estimation Techniques

Xu¹,

Wang²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Traditional methods usually design handcraft feature detection and description for keypoint matching [7,8,9]. In these methods, feature detection and description are two sequential steps that is called detect-then-describe in [10,11]. In this scheme, feature description is the following step after keypoint detection.…”

Section: Introductionmentioning

confidence: 99%

“…The reliability of descriptions in matching should be an important reference for keypoint detection. Based on similar idea, recent works has made some exploration by using detectto-describe [11] or detect-and-describe [10] schemes. The detect-to-describe [11] scheme directly generates saliency maps from feature description for final keypoint detection.…”

Section: Introductionmentioning

confidence: 99%

“…Based on similar idea, recent works has made some exploration by using detectto-describe [11] or detect-and-describe [10] schemes. The detect-to-describe [11] scheme directly generates saliency maps from feature description for final keypoint detection. The handcrafted saliency map is based on the saliency of descriptors information rather than the reliability of descriptors in matching.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DGD-net: Local Descriptor Guided Keypoint Detection Network

Liu

Meng

Tian

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

In recent years, learning-based feature detection network has greatly improved the performance of keypoints matching. However, existing approaches have not fully utilized the representational ability of learned descriptors for feature detection. We propose a novel keypoint detection and description approach to make more use of the reliability of descriptors in matching on keypoint detection. We utilize the descriptor training loss to construct a guided score, which depicts the matching reliability of the descriptors, to supervise the detectors learning. We also propose a descriptor training loss to adapt to our detector training. In order to improve localization accuracy from the low-resolution feature map, we propose a method based on the idea of backtracking. Extensive experiments show the effectiveness of the proposed approach.

show abstract

“…score patches. And some others [13], [14], [20], [21] define the score map based on the distribution of dense feature map.…”

Section: Introductionmentioning

confidence: 99%

ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction

Zhao¹,

Wu²,

Miao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Existing methods detect the keypoints in a nondifferentiable way, therefore they can not directly optimize the position of keypoints through back-propagation. To address this issue, we present a differentiable keypoint detection module, which outputs accurate sub-pixel keypoints. The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization. We also extract the descriptors in a sub-pixel way, and they are trained with the stable neural reprojection error loss. Moreover, a lightweight network is designed for keypoint detection and descriptor extraction, which can run at 95 frames per second for 640×480 images on a commercial GPU. On homography estimation, camera pose estimation, and visual (re-)localization tasks, the proposed method achieves equivalent performance with the state-of-the-art approaches, while greatly reduces the inference time.

show abstract

D2D: Keypoint Extraction with Describe to Detect Approach

Cited by 47 publications

References 49 publications

A Critical Analysis of Image-based Camera Pose Estimation Techniques

A Critical Analysis of Image-based Camera Pose Estimation Techniques

DGD-net: Local Descriptor Guided Keypoint Detection Network

ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction

Contact Info

Product

Resources

About