Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching

• URL: http://arxiv.org/abs/2112.10485v1
• Date: Mon, 20 Dec 2021 12:35:36 GMT
• Title: Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching
• Authors: Yujie Fu, Yihong Wu
• Abstract summary: We propose a scale-difference-aware image matching method (SDAIM) that reduces image scale differences before local feature extraction. In order to accurately estimate the scale ratio, we propose a covisibility-attention-reinforced matching module (CVARM) and then design a novel neural network, termed as Scale-Net.
• Score: 7.297352404640492
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most image matching methods perform poorly when encountering large scale changes in images. To solve this problem, firstly, we propose a scale-difference-aware image matching method (SDAIM) that reduces image scale differences before local feature extraction, via resizing both images of an image pair according to an estimated scale ratio. Secondly, in order to accurately estimate the scale ratio, we propose a covisibility-attention-reinforced matching module (CVARM) and then design a novel neural network, termed as Scale-Net, based on CVARM. The proposed CVARM can lay more stress on covisible areas within the image pair and suppress the distraction from those areas visible in only one image. Quantitative and qualitative experiments confirm that the proposed Scale-Net has higher scale ratio estimation accuracy and much better generalization ability compared with all the existing scale ratio estimation methods. Further experiments on image matching and relative pose estimation tasks demonstrate that our SDAIM and Scale-Net are able to greatly boost the performance of representative local features and state-of-the-art local feature matching methods.

Related papers

• PRISM: PRogressive dependency maxImization for Scale-invariant image Matching [4.9521269535586185]
  We propose PRogressive dependency maxImization for Scale-invariant image Matching (PRISM) Our method's superior matching performance and generalization capability are confirmed by leading accuracy across various evaluation benchmarks and downstream tasks.
  arXiv  Detail & Related papers  (2024-08-07T07:35:17Z)
• AMSA-UNet: An Asymmetric Multiple Scales U-net Based on Self-attention for Deblurring [7.00986132499006]
  asymmetric multiple scales U-net based on self-attention (AMSA-UNet) is proposed to improve the accuracy and computational complexity. By introducing a multiple-scales U shape architecture, the network can focus on blurry regions at the global level and better recover image details at the local level.
  arXiv  Detail & Related papers  (2024-06-13T11:39:02Z)
• Multi-scale Unified Network for Image Classification [33.560003528712414]
  CNNs face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale image inputs. We propose Multi-scale Unified Network (MUSN) consisting of multi-scales, a unified network, and scale-invariant constraint. MUSN yields an accuracy increase up to 44.53% and diminishes FLOPs by 7.01-16.13% in multi-scale scenarios.
  arXiv  Detail & Related papers  (2024-03-27T06:40:26Z)
• Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search [66.95134080902717]
  We propose a novel one-step framework, named Self-similarity driven Scale-invariant Learning (SSL) We introduce a Multi-scale Exemplar Branch to guide the network in concentrating on the foreground and learning scale-invariant features. Experiments on PRW and CUHK-SYSU databases demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2023-02-25T04:48:11Z)
• Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning [55.762840052788945]
  We present Scale-MAE, a pretraining method that explicitly learns relationships between data at different, known scales. We find that tasking the network with reconstructing both low/high frequency images leads to robust multiscale representations for remote sensing imagery.
  arXiv  Detail & Related papers  (2022-12-30T03:15:34Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation [69.45176408639483]
  We reform the conv layer by resorting to the scale-space theory. We build a novel style named SCale AttentioN Conv Neural Network (textbfSCAN-CNN) As a single-shot scheme, the inference is more efficient than multi-shot fusion.
  arXiv  Detail & Related papers  (2022-09-19T06:35:04Z)
• Self-Supervised Learning of Image Scale and Orientation [35.94215211409985]
  We study the problem of learning to assign a characteristic pose, i.e., scale and orientation, for an image region of interest. It is hard to obtain a large-scale set of image regions with explicit pose annotations that a model directly learns from. We propose a self-supervised learning framework with a histogram alignment technique.
  arXiv  Detail & Related papers  (2022-06-15T02:43:39Z)
• ScaleNet: A Shallow Architecture for Scale Estimation [25.29257353644138]
  We design a new architecture, ScaleNet, that exploits dilated convolutions and self and cross-correlation layers to predict the scale between images. We show how ScaleNet can be combined with sparse local features and dense correspondence networks to improve camera pose estimation, 3D reconstruction, or dense geometric matching.
  arXiv  Detail & Related papers  (2021-12-09T11:32:01Z)
• Image Matching with Scale Adjustment [57.18604132027697]
  We show how to represent and extract interest points at variable scales. We devise a method allowing the comparison of two images at two different resolutions.
  arXiv  Detail & Related papers  (2020-12-10T11:03:25Z)
• Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer [116.46533207849619]
  We study the impact of scale and location mismatch in the few-shot learning scenario. We propose a novel Spatially-aware Matching scheme to effectively perform matching across multiple scales and locations.
  arXiv  Detail & Related papers  (2020-01-06T14:10:20Z)

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.