Fully Convolutional Line Parsing
- URL: http://arxiv.org/abs/2104.11207v2
- Date: Fri, 23 Apr 2021 03:37:21 GMT
- Title: Fully Convolutional Line Parsing
- Authors: Xili Dai, Xiaojun Yuan, Haigang Gong, Yi Ma
- Abstract summary: We present a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images.
F-Clip detects line segments in an end-to-end fashion by predicting them with each line's center position, length, and angle.
We conduct extensive experiments and show that our method achieves a significantly better trade-off between efficiency and accuracy.
- Score: 25.80938920093857
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: We present a one-stage Fully Convolutional Line Parsing network (F-Clip) that
detects line segments from images. The proposed network is very simple and
flexible with variations that gracefully trade off between speed and accuracy
for different applications. F-Clip detects line segments in an end-to-end
fashion by predicting them with each line's center position, length, and angle.
Based on empirical observation of the distribution of line angles in real image
datasets, we further customize the design of convolution kernels of our fully
convolutional network to effectively exploit such statistical priors. We
conduct extensive experiments and show that our method 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. Such inference speed makes our method
readily applicable to real-time tasks without compromising any accuracy of
previous methods. Moreover, when equipped with a performance-improving backbone
network, F-Clip is able to significantly outperform all state-of-the-art line
detectors on accuracy at a similar or even higher frame rate. Source code
https://github.com/Delay-Xili/F-Clip.
Related papers
- TAPIR: Tracking Any Point with per-frame Initialization and temporal
Refinement [64.11385310305612]
We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence.
Our approach employs two stages: (1) a matching stage, which independently locates a suitable candidate point match for the query point on every other frame, and (2) a refinement stage, which updates both the trajectory and query features based on local correlations.
The resulting model surpasses all baseline methods by a significant margin on the TAP-Vid benchmark, as demonstrated by an approximate 20% absolute average Jaccard (AJ) improvement on DAVIS.
arXiv Detail & Related papers (2023-06-14T17:07:51Z) - 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) - Detecting Line Segments in Motion-blurred Images with Events [38.39698414942873]
Existing line segment detection methods face severe performance degradation when detecting line segments when motion blur occurs.
We propose to leverage the complementary information of images and events to robustly detect line segments over motion blurs.
Our method achieves 63.3% mean structural average precision (msAP) with the model pre-trained on the FE-Wireframe and fine-tuned on the FE-Blurframe.
arXiv Detail & Related papers (2022-11-14T14:00:03Z) - Real-Time Scene Text Detection with Differentiable Binarization and
Adaptive Scale Fusion [62.269219152425556]
segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field.
We propose a Differentiable Binarization (DB) module that integrates the binarization process into a segmentation network.
An efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively.
arXiv Detail & Related papers (2022-02-21T15:30:14Z) - AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally
Consistent Video Semantic Segmentation [81.87943324048756]
In video segmentation, generating temporally consistent results across frames is as important as achieving frame-wise accuracy.
Existing methods rely on optical flow regularization or fine-tuning with test data to attain temporal consistency.
This paper presents an efficient, intuitive, and unsupervised online adaptation method, AuxAdapt, for improving the temporal consistency of most neural network models.
arXiv Detail & Related papers (2021-10-24T07:07:41Z) - 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) - ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and
Spherical Cameras [17.943949895764938]
Line segment detection is essential for high-level tasks in computer vision and robotics.
Currently, most stateof-the-art (SOTA) methods are dedicated to detecting straight line segments in undistorted pinhole images.
We propose to target at the unified line segment detection (ULSD) for both distorted and undistorted images.
arXiv Detail & Related papers (2020-11-06T03:30:17Z) - Holistically-Attracted Wireframe Parsing [123.58263152571952]
This paper presents a fast and parsimonious parsing method to detect a vectorized wireframe in an input image with a single forward pass.
The proposed method is end-to-end trainable, consisting of three components: (i) line segment and junction proposal generation, (ii) line segment and junction matching, and (iii) line segment and junction verification.
arXiv Detail & Related papers (2020-03-03T17:43:57Z) - Directional Deep Embedding and Appearance Learning for Fast Video Object
Segmentation [11.10636117512819]
We propose a directional deep embedding and YouTube appearance learning (DEmbed) method, which is free of the online fine-tuning process.
Our method achieves a state-of-the-art VOS performance without using online fine-tuning.
arXiv Detail & Related papers (2020-02-17T01:51:57Z)
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.