Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

@article{Laguna2019KeyNetKD,
  title={Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters},
  author={Axel Barroso Laguna and Edgar Riba and Daniel Ponsa and Krystian Mikolajczyk},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={5835-5843}
}
We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. [...] Key Method Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchmark. Results show…Expand
Learning of low-level feature keypoints for accurate and robust detection
TLDR
The detector is a single CNN layer extended from the descriptor backbone, which can be jointly learned with the descriptor for maximizing the descriptor matching, and results in a state-of-the-art 3D reconstruction, especially on improving reprojection error, and the highest accuracy in keypoint detection and matching on benchmark datasets. Expand
Realtime CNN-based Keypoint Detector with Sobel Filter and CNN-based Descriptor Trained with Keypoint Candidates
TLDR
This paper introduces two separate CNNs, lightweight SobelNet and DesNet, to detect key points and to compute dense local descriptors to achieve better or comparable performance with less computation compared with SOTA methods in recent years. Expand
UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision
In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without theExpand
Learning to Detect Local Features Using Information Change
TLDR
This paper proposes a trainable information accumulation pyramid that allows us to relate the change in the receptive field with information change, and demonstrates the efficacy of the proposed keypoint extractor by evaluating its performance for repeatability and matching scores. Expand
ASLFeat: Learning Local Features of Accurate Shape and Localization
  • Zixin Luo, Lei Zhou, +6 authors Long Quan
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors, by resorting to deformable convolutional networks to densely estimate and apply local transformation in ASLFeat. Expand
Automatic Sparsity-Aware Recognition for Keypoint Detection
  • Yurui Xie, L. Guan
  • Computer Science
  • 2020 IEEE International Symposium on Multimedia (ISM)
  • 2020
TLDR
A novel Sparsity-Aware Keypoint detector (SAKD) to localize a set of discriminative keypoints via optimization of group-sparse coding that achieves favorable performances compared with state-of-the-art in literature. Expand
R2D2: Repeatable and Reliable Detector and Descriptor
TLDR
This work argues that salient regions are not necessarily discriminative, and therefore can harm the performance of the description, and proposes to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness. Expand
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
TLDR
A new training methodology is proposed which embeds the feature detector in a complete vision pipeline, and where the learnable parameters are trained in an end-to-end fashion, and demonstrates that the accuracy of a state-of-the-art learning-based feature detector can be increased when trained for the task it is supposed to solve at test time. Expand
SEKD: Self-Evolving Keypoint Detection and Description
TLDR
A self-supervised framework, namely self-evolving keypoint detection and description (SEKD), is proposed to learn an advanced local feature model from unlabeled natural images that outperforms popular hand-crafted and DNN-based methods by remarkable margins. Expand
D2D: Keypoint Extraction with Describe to Detect Approach
TLDR
A novel approach that exploits the information within the descriptor space to propose keypoint locations and improves the matching performance of various descriptors and that it generalises across methods and tasks. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 51 REFERENCES
TILDE: A Temporally Invariant Learned DEtector
We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisinglyExpand
MatchNet: Unifying feature and metric learning for patch-based matching
TLDR
A unified approach to combining feature computation and similarity networks for training a patch matching system that improves accuracy over previous state-of-the-art results on patch matching datasets, while reducing the storage requirement for descriptors is confirmed. Expand
LF-Net: Learning Local Features from Images
TLDR
A novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision, and shows that it can optimize the network in a two-branch setup by confining it to one branch, while preserving differentiability in the other. Expand
Learning to compare image patches via convolutional neural networks
TLDR
This paper shows how to learn directly from image data a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems, and opts for a CNN-based model that is trained to account for a wide variety of changes in image appearance. Expand
LIFT: Learned Invariant Feature Transform
TLDR
This work introduces a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description, and shows how to learn to do all three in a unified manner while preserving end-to-end differentiability. Expand
HPatches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors
TLDR
A novel benchmark for evaluating local image descriptors is proposed and it is shown 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. Expand
Learning to Find Good Correspondences
TLDR
A novel normalization technique, called Context Normalization, is introduced, which allows the network to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences. Expand
SuperPoint: Self-Supervised Interest Point Detection and Description
TLDR
This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision and introduces Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation. Expand
Learning to Assign Orientations to Feature Points
TLDR
This work shows how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point, and proposes a new type of activation function for Neural Networks that generalizes the popular ReLU, maxout, and PReLU activation functions. Expand
End-to-End Learning of Keypoint Detector and Descriptor for Pose Invariant 3D Matching
TLDR
An end-to-end learning framework for keypoint detection and its representation (descriptor) for 3D depth maps or 3D scans is proposed, where the two can be jointly optimized towards task-specific objectives without a need for separate annotations. Expand
...
1
2
3
4
5
...