PPGNet: Learning Point-Pair Graph for Line Segment Detection

@article{Zhang2019PPGNetLP,
  title={PPGNet: Learning Point-Pair Graph for Line Segment Detection},
  author={Ziheng Zhang and Zhengxin Li and Ning Bi and Jia Zheng and Jinlei Wang and Kun Huang and Weixin Luo and Yanyu Xu and Shenghua Gao},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={7098-7107}
}
In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods. In order to extract a line segment graph from an image, we further introduce the PPGNet, a convolutional neural network that directly infers a graph from an image. We… Expand
TP-LSD: Tri-Points Based Line Segment Detector
TLDR
This paper proposes a novel deep convolutional model, Tri-Points Based Line Segment Detector (TP-LSD), to detect line segments in an image at real-time speed, and introduces the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment. Expand
Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Classification
TLDR
A 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image, and a novel algorithm utilizing convolutional neural networks that detects geometric primitives and classifies their relationships. Expand
Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference
TLDR
A 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image, and a novel algorithm utilizing convolutional neural networks that detects geometric primitives and infers their relationships. Expand
Fully Convolutional Line Parsing
TLDR
This work presents a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images and achieves a significantly better trade-off between efficiency and accuracy, resulting in a real-time line detector at up to 73 FPS on a single GPU. Expand
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
TLDR
Experimental results validate the superiority of the proposed ULSD to the SOTA methods both in accuracy and efficiency (40.6fps for pinhole images). Expand
Deep Hough Transform for Semantic Line Detection
TLDR
The problem of detecting semantic lines in the spatial domain is transformed to spotting individual points in the parametric domain, making the post-processing steps, i.e., non-maximal suppression, more efficient. Expand
Deep Hough Transform for Semantic Line Detection
In this paper, we put forward a simple yet effective method to detect meaningful straight lines, a.k.a. semantic lines, in given scenes. Prior methods take line detection as a special case of objectExpand
Line Segment Detection Using Transformers without Edges
TLDR
A joint end-to-end line segment detection algorithm using Transformers that is postprocessing and heuristics-guided intermediate processing (edge/junction/region detection) free and takes advantages of having integrated tokenized queries, a self-attention mechanism, and encoding-decoding strategy within Transformers. Expand
ELSD: Efficient Line Segment Detector and Descriptor
TLDR
The novel Efficient Line Segment Detector and Descriptor (ELSD) to simultaneously detect line segments and extract their descriptors in an image achieves the state-of-the-art performance on the Wireframe dataset and YorkUrban dataset, in both accuracy and efficiency. Expand
Wireframe Parsing With Guidance of Distance Map
TLDR
Experimental results show that the proposed end-to-end method for simultaneously detecting local junctions and global wireframe in man-made environment outperforms the previous state-of-the-art wireframe parser by a descent margin. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 65 REFERENCES
Learning to Parse Wireframes in Images of Man-Made Environments
TLDR
A learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments and two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support are proposed. Expand
Associative Embedding: End-to-End Learning for Joint Detection and Grouping
TLDR
Associative embedding is introduced, a novel method for supervising convolutional neural networks for the task of detection and grouping for multi-person pose estimation and state-of-the-art performance on the MPII and MS-COCO datasets is reported. Expand
CannyLines: A parameter-free line segment detector
  • X. Lu, Jian Yao, K. Li, L. Li
  • Mathematics, Computer Science
  • 2015 IEEE International Conference on Image Processing (ICIP)
  • 2015
TLDR
Experimental results illustrate that the proposed line segment detector, named as CannyLines, can extract more meaningful line segments than two popularly used line segment detectors, LSD and ED-L lines, especially on the man-made scenes. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Scene Parsing through ADE20K Dataset
TLDR
The ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts, is introduced and it is shown that the trained scene parsing networks can lead to applications such as image content removal and scene synthesis. Expand
Pixels to Graphs by Associative Embedding
TLDR
A method for training a convolutional neural network such that it takes in an input image and produces a full graph definition and is done end-to-end in a single stage with the use of associative embeddings. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Efficient 3D scene abstraction using line segments
TLDR
A robust and efficient line-based Multi-v iew Stereo algorithm is introduced that uses geometric line-matching, which makes it invariant to illumination changes, and generates accurate 3D models with low computational costs, which is especially useful for large-scale urban datasets. Expand
A generalisable framework for saliency-based line segment detection
TLDR
A novel, information-theoretic salient line segment detector that naturally avoids the repetitive parts of a scene while detecting the strong, discriminative lines present, and is highly generalisable, depending only on image statistics rather than image gradient. Expand
MCMLSD: A Dynamic Programming Approach to Line Segment Detection
TLDR
A probabilistic algorithm that merges the advantages of both the Hough and Markov approaches to line segment detection and develops and applies a novel quantitative evaluation methodology that controls for under-and over-segmentation. Expand
...
1
2
3
4
5
...