EpiMask: Leveraging Epipolar Distance Based Masks in Cross-Attention for Satellite Image Matching

• URL: http://arxiv.org/abs/2603.21463v1
• Date: Mon, 23 Mar 2026 00:48:58 GMT
• Title: EpiMask: Leveraging Epipolar Distance Based Masks in Cross-Attention for Satellite Image Matching
• Abstract summary: Deep-learning based image matching networks can handle significantly larger variations in viewpoints and illuminations.<n>We present EpiMask, a semi-dense image matching network for satellite images.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The deep-learning based image matching networks can now handle significantly larger variations in viewpoints and illuminations while providing matched pairs of pixels with sub-pixel precision. These networks have been trained with ground-based image datasets and, implicitly, their performance is optimized for the pinhole camera geometry. Consequently, you get suboptimal performance when such networks are used to match satellite images since those images are synthesized as a moving satellite camera records one line at a time of the points on the ground. In this paper, we present EpiMask, a semi-dense image matching network for satellite images that (1) Incorporates patch-wise affine approximations to the camera modeling geometry; (2) Uses an epipolar distance-based attention mask to restrict cross-attention to geometrically plausible regions; and (3) That fine-tunes a foundational pretrained image encoder for robust feature extraction. Experiments on the SatDepth dataset demonstrate up to 30% improvement in matching accuracy compared to re-trained ground-based models.

Related papers

• Component-Aware Structure-Preserving Style Transfer for Satellite Visual Sim2Real Data Construction [7.240627719297504]
  This paper presents a structure-preserving style transfer framework for satellite visual synthetic-to-real data construction.<n>The proposed method achieves the lowest image distribution discrepancy, with an FID of 54.32 and a KID of 0.048.
  arXiv  Detail & Related papers  (2026-05-19T10:01:17Z)
• SatDepth: A Novel Dataset for Satellite Image Matching [0.0]
  We present SatDepth'', a novel dataset that provides dense ground-truth correspondences for training image matching frameworks for satellite images.<n>We benchmark four existing image matching frameworks using our dataset and carry out an ablation study that confirms that the models trained with our dataset with rotation augmentation outperform (up to 40% increase in precision) the models trained with other datasets.
  arXiv  Detail & Related papers  (2025-03-17T00:14:13Z)
• Weakly-supervised Camera Localization by Ground-to-satellite Image Registration [52.54992898069471]
  We propose a weakly supervised learning strategy for ground-to-satellite image registration. It derives positive and negative satellite images for each ground image. We also propose a self-supervision strategy for cross-view image relative rotation estimation.
  arXiv  Detail & Related papers  (2024-09-10T12:57:16Z)
• SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation [53.83313235792596]
  We present a new methodology for real-time semantic mapping from RGB-D sequences. It combines a 2D neural network and a 3D network based on a SLAM system with 3D occupancy mapping. Our system achieves state-of-the-art semantic mapping quality within 2D-3D networks-based systems.
  arXiv  Detail & Related papers  (2023-06-28T22:36:44Z)
• SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation [7.751856268560216]
  SliceMatch consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor.
  arXiv  Detail & Related papers  (2022-11-26T20:06:20Z)
• PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanism [4.822598110892846]
  Existing deep calibrated photometric stereo networks aggregate observations under different lights based on pre-defined operations such as linear projection and max pooling. To tackle this issue, this paper presents a deep sparse calibrated photometric stereo network named it PS-Transformer which leverages the learnable self-attention mechanism to properly capture the complex inter-image interactions.
  arXiv  Detail & Related papers  (2022-11-21T11:58:25Z)
• Extracting Triangular 3D Models, Materials, and Lighting From Images [59.33666140713829]
  We present an efficient method for joint optimization of materials and lighting from multi-view image observations. We leverage meshes with spatially-varying materials and environment that can be deployed in any traditional graphics engine.
  arXiv  Detail & Related papers  (2021-11-24T13:58:20Z)
• Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo [61.6260594326246]
  We introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. Using separable 4D convolutions and 2D heat-maps reduces the size and makes more efficient.
  arXiv  Detail & Related papers  (2021-03-22T18:06:58Z)
• Fast Single-shot Ship Instance Segmentation Based on Polar Template Mask in Remote Sensing Images [7.45725819658858]
  We propose a single-shot convolutional neural network structure, which is conceptually simple and straightforward. Our method, termed with SSS-Net, detects targets based on the location of the object's center. Experiments on both the Airbus Ship Detection Challenge dataset and the ISAIDships dataset show that SSS-Net has strong competitiveness in precision and speed for ship instance segmentation.
  arXiv  Detail & Related papers  (2020-08-28T02:38:04Z)
• Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images [59.906948203578544]
  We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object. We first estimate per-view depth maps using a deep multi-view stereo network. These depth maps are used to coarsely align the different views. We propose a novel multi-view reflectance estimation network architecture.
  arXiv  Detail & Related papers  (2020-03-27T21:28:54Z)
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes [98.65457534223539]
  We propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes. The proposed method achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps.
  arXiv  Detail & Related papers  (2020-03-11T08:45:53Z)

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.