Automatic High Resolution Wire Segmentation and Removal

• URL: http://arxiv.org/abs/2304.00221v1
• Date: Sat, 1 Apr 2023 04:24:12 GMT
• Title: Automatic High Resolution Wire Segmentation and Removal
• Abstract summary: Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. We present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds.
• Score: 54.65877883437031
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wires and powerlines are common visual distractions that often undermine the aesthetics of photographs. The manual process of precisely segmenting and removing them is extremely tedious and may take up hours, especially on high-resolution photos where wires may span the entire space. In this paper, we present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds. We observe several unique challenges: wires are thin, lengthy, and sparse. These are rare properties of subjects that common segmentation tasks cannot handle, especially in high-resolution images. We thus propose a two-stage method that leverages both global and local contexts to accurately segment wires in high-resolution images efficiently, and a tile-based inpainting strategy to remove the wires given our predicted segmentation masks. We also introduce the first wire segmentation benchmark dataset, WireSegHR. Finally, we demonstrate quantitatively and qualitatively that our wire clean-up system enables fully automated wire removal with great generalization to various wire appearances.

Related papers

• Autonomously Unweaving Multiple Cables Using Visual Feedback [27.549099502088875]
  Cables are deformable and can have combinations of knots and multiple interwoven segments.<n>We propose a method that utilizes visual feedback to unweave a bundle of loosely entangled cables.<n>We experimentally demonstrate that iterating the above perception-planning-action process enables unweaving electric cables and shoelaces with an 84% success rate.
  arXiv  Detail & Related papers  (2025-12-13T21:42:45Z)
• POEv2: a flexible and robust framework for generic line segment detection and wireframe line segment detection [11.8193704397315]
  Line segment detectors can be divided into two categories: generic line segment detectors and wireframe line segment detectors.<n>Recent deep learning based approaches are mostly wireframe line segment detectors.<n>We propose a robust framework that can be used for both generic line segment detection and wireframe line segment detection.
  arXiv  Detail & Related papers  (2025-08-27T10:13:46Z)
• Deep Generative Adversarial Network for Occlusion Removal from a Single Image [3.5639148953570845]
  We propose a fully automatic, two-stage convolutional neural network for fence segmentation and occlusion completion. We leverage generative adversarial networks (GANs) to synthesize realistic content, including both structure and texture, in a single shot for inpainting.
  arXiv  Detail & Related papers  (2024-09-20T06:00:45Z)
• Raformer: Redundancy-Aware Transformer for Video Wire Inpainting [77.41727407673066]
  Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series. Wire removal poses greater challenges due to the wires being longer and slimmer than objects typically targeted in general video inpainting tasks. We introduce a new VWI dataset with a novel mask generation strategy, namely Wire Removal Video dataset 2 (WRV2) and Pseudo Wire-Shaped (PWS) Masks. WRV2 dataset comprises over 4,000 videos with an average length of 80 frames, designed to facilitate the development and efficacy of inpainting models.
  arXiv  Detail & Related papers  (2024-04-24T11:02:13Z)
• DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients [105.25109274550607]
  Line segments are increasingly used in vision tasks. Traditional line detectors based on the image gradient are extremely fast and accurate, but lack robustness in noisy images and challenging conditions. We propose to combine traditional and learned approaches to get the best of both worlds: an accurate and robust line detector.
  arXiv  Detail & Related papers  (2022-12-15T12:36:49Z)
• Unbiased Multi-Modality Guidance for Image Inpainting [27.286351511243502]
  We develop an end-to-end multi-modality guided transformer network for image inpainting. Within each transformer block, the proposed spatial-aware attention module can learn the multi-modal structural features efficiently. Our method enriches semantically consistent context in an image based on discriminative information from multiple modalities.
  arXiv  Detail & Related papers  (2022-08-25T03:13:43Z)
• SOLD2: Self-supervised Occlusion-aware Line Description and Detection [95.8719432775724]
  We introduce the first joint detection and description of line segments in a single deep network. Our method does not require any annotated line labels and can therefore generalize to any dataset. We evaluate our approach against previous line detection and description methods on several multi-view datasets.
  arXiv  Detail & Related papers  (2021-04-07T19:27:17Z)
• Learning to Parse Wireframes in Images of Man-Made Environments [40.471924713855735]
  We propose a "wireframe"-based approach to the task of representation for manmade environments. We have built networks that are suitable for extracting two large lines and their junctions.
  arXiv  Detail & Related papers  (2020-07-15T07:54:18Z)
• Wavelet-Based Dual-Branch Network for Image Demoireing [148.91145614517015]
  We design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoireing. Our network removes moire patterns in the wavelet domain to separate the frequencies of moire patterns from the image content. Experiments demonstrate the effectiveness of our method, and we further show that WDNet generalizes to removing moire artifacts on non-screen images.
  arXiv  Detail & Related papers  (2020-07-14T16:44:30Z)
• Gated Fusion Network for Degraded Image Super Resolution [78.67168802945069]
  We propose a dual-branch convolutional neural network to extract base features and recovered features separately. By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process.
  arXiv  Detail & Related papers  (2020-03-02T13:28:32Z)

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.