ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

• URL: http://arxiv.org/abs/2208.14201v1
• Date: Tue, 30 Aug 2022 12:21:15 GMT
• Title: ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
• Authors: Hongkai Chen, Zixin Luo, Lei Zhou, Yurun Tian, Mingmin Zhen, Tian Fang, David Mckinnon, Yanghai Tsin, Long Quan
• Abstract summary: ASpanFormer is a Transformer-based detector-free matcher that is built on hierarchical attention structure. We propose a novel attention operation which is capable of adjusting attention span in a self-adaptive manner. By these means, we are able to not only maintain long-range dependencies, but also enable fine-grained attention among pixels of high relevance.
• Score: 33.603064903549985
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher that is built on hierarchical attention structure, adopting a novel attention operation which is capable of adjusting attention span in a self-adaptive manner. To achieve this goal, first, flow maps are regressed in each cross attention phase to locate the center of search region. Next, a sampling grid is generated around the center, whose size, instead of being empirically configured as fixed, is adaptively computed from a pixel uncertainty estimated along with the flow map. Finally, attention is computed across two images within derived regions, referred to as attention span. By these means, we are able to not only maintain long-range dependencies, but also enable fine-grained attention among pixels of high relevance that compensates essential locality and piece-wise smoothness in matching tasks. State-of-the-art accuracy on a wide range of evaluation benchmarks validates the strong matching capability of our method.

Related papers

• Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registration [4.954184310509112]
  Image-to-point cloud registration aims to determine the relative camera pose between an RGB image and a reference point cloud. Matching individual points with pixels can be inherently ambiguous due to modality gaps. We propose a framework to capture quantity-aware correspondences between local point sets and pixel patches.
  arXiv  Detail & Related papers  (2023-07-14T03:55:54Z)
• Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network [52.29330138835208]
  Accurately matching local features between a pair of images is a challenging computer vision task. Previous studies typically use attention based graph neural networks (GNNs) with fully-connected graphs over keypoints within/across images. We propose MaKeGNN, a sparse attention-based GNN architecture which bypasses non-repeatable keypoints and leverages matchable ones to guide message passing.
  arXiv  Detail & Related papers  (2023-07-04T02:50:44Z)
• Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints [44.90917854990362]
  We propose a transformer-based cascade matching model -- Cascade feature Matching TRansformer (CasMTR) We use a simple yet effective Non-Maximum Suppression (NMS) post-process to filter keypoints through the confidence map. CasMTR achieves state-of-the-art performance in indoor and outdoor pose estimation as well as visual localization.
  arXiv  Detail & Related papers  (2023-03-06T04:32:34Z)
• Location-Aware Self-Supervised Transformers [74.76585889813207]
  We propose to pretrain networks for semantic segmentation by predicting the relative location of image parts. We control the difficulty of the task by masking a subset of the reference patch features visible to those of the query. Our experiments show that this location-aware pretraining leads to representations that transfer competitively to several challenging semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2022-12-05T16:24:29Z)
• LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity [49.84167231111667]
  Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image. We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion. We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
  arXiv  Detail & Related papers  (2022-04-06T17:48:18Z)
• DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points [15.953570826460869]
  Establishing dense correspondence between two images is a fundamental computer vision problem. We introduce DenseGAP, a new solution for efficient Dense correspondence learning with a Graph-structured neural network conditioned on Anchor Points. Our method advances the state-of-the-art of correspondence learning on most benchmarks.
  arXiv  Detail & Related papers  (2021-12-13T18:59:30Z)
• COTR: Correspondence Transformer for Matching Across Images [31.995943755283786]
  We propose a novel framework for finding correspondences in images based on a deep neural network. By doing so, one has the option to query only the points of interest and retrieve sparse correspondences, or to query all points in an image and obtain dense mappings.
  arXiv  Detail & Related papers  (2021-03-25T22:47:02Z)
• Align Deep Features for Oriented Object Detection [40.28244152216309]
  We propose a single-shot Alignment Network (S$2$A-Net) consisting of two modules: a Feature Alignment Module (FAM) and an Oriented Detection Module (ODM) The FAM can generate high-quality anchors with an Anchor Refinement Network and adaptively align the convolutional features according to the anchor boxes with a novel Alignment Convolution. The ODM first adopts active rotating filters to encode the orientation information and then produces orientation-sensitive and orientation-invariant features to alleviate the inconsistency between classification score and localization accuracy.
  arXiv  Detail & Related papers  (2020-08-21T09:55:13Z)
• Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector [95.51517606475376]
  A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. We propose a domain adaptation framework that accounts for each pixel via predicting pixel-wise objectness and centerness.
  arXiv  Detail & Related papers  (2020-08-19T17:57:03Z)
• Inter-Image Communication for Weakly Supervised Localization [77.2171924626778]
  Weakly supervised localization aims at finding target object regions using only image-level supervision. We propose to leverage pixel-level similarities across different objects for learning more accurate object locations. Our method achieves the Top-1 localization error rate of 45.17% on the ILSVRC validation set.
  arXiv  Detail & Related papers  (2020-08-12T04:14:11Z)
• Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching [95.64702426906466]
  Cross-view geo-localization is a problem given a large-scale database of geo-tagged aerial images. Knowing orientation between ground and aerial images can significantly reduce matching ambiguity between these two views. We design a Dynamic Similarity Matching network to estimate cross-view orientation alignment during localization.
  arXiv  Detail & Related papers  (2020-05-08T05:21:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.