End-to-End Wireframe Parsing

@article{Zhou2019EndtoEndWP,
  title={End-to-End Wireframe Parsing},
  author={Yichao Zhou and Haozhi Qi and Y. Ma},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={962-971}
}
  • Yichao Zhou, Haozhi Qi, Y. Ma
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • We present a conceptually simple yet effective algorithm to detect wireframes in a given image. Compared to the previous methods which first predict an intermediate heat map and then extract straight lines with heuristic algorithms, our method is end-to-end trainable and can directly output a vectorized wireframe that contains semantically meaningful and geometrically salient junctions and lines. To better understand the quality of the outputs, we propose a new metric for wireframe evaluation… CONTINUE READING
    Holistically-Attracted Wireframe Parsing
    • 1
    • Highly Influenced
    • PDF
    Wireframe Parsing With Guidance of Distance Map
    • 1
    • PDF
    NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
    • 5
    • PDF
    TP-LSD: Tri-Points Based Line Segment Detector
    • 1
    • Highly Influenced
    • PDF
    Neural Wireframe Renderer: Learning Wireframe to Image Translations
    A simplified pipeline for line segment detection
    Robust Line Segments Matching via Graph Convolution Networks
    LGNN: A Context-aware Line Segment Detector
    Deep Hough-Transform Line Priors
    • 1
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES
    Learning to Parse Wireframes in Images of Man-Made Environments
    • 37
    • Highly Influential
    • PDF
    Learning to Reconstruct 3D Manhattan Wireframes From a Single Image
    • 9
    • PDF
    Lifting 3D Manhattan Lines from a Single Image
    • 53
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,437
    • PDF
    Instance-Aware Semantic Segmentation via Multi-task Network Cascades
    • 729
    • PDF
    LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
    • 83
    • PDF
    Deformable Convolutional Networks
    • 1,170
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,443
    • Highly Influential
    • PDF
    Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery
    • 196
    • Highly Influential
    • PDF
    Recovering 3D Planes from a Single Image via Convolutional Neural Networks
    • 26
    • PDF