ContourRend: A Segmentation Method for Improving Contours by Rendering

• URL: http://arxiv.org/abs/2007.07437v1
• Date: Wed, 15 Jul 2020 02:16:00 GMT
• Title: ContourRend: A Segmentation Method for Improving Contours by Rendering
• Authors: Junwen Chen, Yi Lu, Yaran Chen, Dongbin Zhao, and Zhonghua Pang
• Abstract summary: Mask-based segmentation can not handle contour features well on a coarse prediction grid. We propose Contourend which adopts convolution contour to refine segmentation contours. Our method reaches 72.41% mean intersection over union (IoU) and surpasses baseline Polygon-GCN by 1.22%.
• Score: 10.13129256609938
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A good object segmentation should contain clear contours and complete regions. However, mask-based segmentation can not handle contour features well on a coarse prediction grid, thus causing problems of blurry edges. While contour-based segmentation provides contours directly, but misses contours' details. In order to obtain fine contours, we propose a segmentation method named ContourRend which adopts a contour renderer to refine segmentation contours. And we implement our method on a segmentation model based on graph convolutional network (GCN). For the single object segmentation task on cityscapes dataset, the GCN-based segmentation con-tour is used to generate a contour of a single object, then our contour renderer focuses on the pixels around the contour and predicts the category at high resolution. By rendering the contour result, our method reaches 72.41% mean intersection over union (IoU) and surpasses baseline Polygon-GCN by 1.22%.

Related papers

• Joint Dense-Point Representation for Contour-Aware Graph Segmentation [2.138299283227551]
  We present a novel methodology that combines graph and dense segmentation techniques by jointly learning both point and pixel contour representations. This addresses deficiencies in typical graph segmentation methods where misaligned objectives restrict the network from learning discriminative and contour features. Our approach is validated on several Chest X-ray datasets, demonstrating clear improvements in segmentation stability and accuracy.
  arXiv  Detail & Related papers  (2023-06-21T10:07:17Z)
• PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban Meshes [3.058685580689605]
  We introduce a novel deep learning-based framework to interpret 3D urban scenes represented as textured meshes. Our framework achieves semantic segmentation in two steps: planarity-sensible over-segmentation followed by semantic classification. Our approach outperforms the state-of-the-art methods in terms of boundary quality and mean IoU (intersection over union)
  arXiv  Detail & Related papers  (2022-02-07T14:16:10Z)
• End-to-End Segmentation via Patch-wise Polygons Prediction [93.91375268580806]
  The leading segmentation methods represent the output map as a pixel grid. We study an alternative representation in which the object edges are modeled, per image patch, as a polygon with $k$ vertices that is coupled with per-patch label probabilities.
  arXiv  Detail & Related papers  (2021-12-05T10:42:40Z)
• PSGR: Pixel-wise Sparse Graph Reasoning for COVID-19 Pneumonia Segmentation in CT Images [83.26057031236965]
  We propose a pixel-wise sparse graph reasoning (PSGR) module to enhance the modeling of long-range dependencies for COVID-19 infected region segmentation in CT images. The PSGR module avoids imprecise pixel-to-node projections and preserves the inherent information of each pixel for global reasoning. The solution has been evaluated against four widely-used segmentation models on three public datasets.
  arXiv  Detail & Related papers  (2021-08-09T04:58:23Z)
• ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass [48.57232627854642]
  We argue that the difficulty in regressing the contour points in one pass is mainly due to the ambiguity when discretizing a smooth contour into a polygon. To address the ambiguity, we propose a novel differentiable rendering-based approach named textbfContourRender. It first predicts a contour generated by an invertible shape signature, and then optimize the contour with the more stable silhouette by converting it to a contour mesh and rendering the mesh to a 2D map.
  arXiv  Detail & Related papers  (2021-06-07T07:23:03Z)
• Polygonal Point Set Tracking [50.445151155209246]
  We propose a novel learning-based polygonal point set tracking method. Our goal is to track corresponding points on the target contour. We present visual-effects applications of our method on part distortion and text mapping.
  arXiv  Detail & Related papers  (2021-05-30T17:12:36Z)
• BoundarySqueeze: Image Segmentation as Boundary Squeezing [104.43159799559464]
  We propose a novel method for fine-grained high-quality image segmentation of both objects and scenes. Inspired by dilation and erosion from morphological image processing techniques, we treat the pixel level segmentation problems as squeezing object boundary. Our method yields large gains on COCO, Cityscapes, for both instance and semantic segmentation and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting.
  arXiv  Detail & Related papers  (2021-05-25T04:58:51Z)
• Contour Loss for Instance Segmentation via k-step Distance Transformation Image [5.02853371403908]
  Instance segmentation aims to locate targets in the image and segment each target area at pixel level. Mask R-CNN is a classic method of instance segmentation, but its predicted masks are unclear and inaccurate near contours. We propose a novel loss function, called contour loss, which can assure more accurate instance segmentation.
  arXiv  Detail & Related papers  (2021-02-22T09:35:35Z)
• Geometry Constrained Weakly Supervised Object Localization [55.17224813345206]
  We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization. The detector predicts the object location defined by a set of coefficients describing a geometric shape. The generator takes the resulting masked images as input and performs two complementary classification tasks for the object and background. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing.
  arXiv  Detail & Related papers  (2020-07-19T17:33:42Z)
• Walk the Lines: Object Contour Tracing CNN for Contour Completion of Ships [0.0]
  We develop a new contour tracing algorithm to enhance the results of the latest object contour detectors. The goal is to achieve a perfectly closed, 1 pixel wide and detailed object contour. We present the Walk the Lines (WtL) algorithm, a standard regression CNN trained to follow object contours.
  arXiv  Detail & Related papers  (2020-04-14T15:19:04Z)

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.