Field of Junctions: Extracting Boundary Structure at Low SNR

• URL: http://arxiv.org/abs/2011.13866v3
• Date: Thu, 11 Nov 2021 16:13:54 GMT
• Title: Field of Junctions: Extracting Boundary Structure at Low SNR
• Authors: Dor Verbin and Todd Zickler
• Abstract summary: We introduce a bottom-up detector for simultaneously finding many boundary elements in an image, including contours, corners and junctions. Notably, its analysis of contours, corners, junctions and uniform regions allows it to succeed at high noise levels, where other methods for boundary detection fail.
• Score: 5.584060970507507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a bottom-up model for simultaneously finding many boundary elements in an image, including contours, corners and junctions. The model explains boundary shape in each small patch using a 'generalized M-junction' comprising M angles and a freely-moving vertex. Images are analyzed using non-convex optimization to cooperatively find M+2 junction values at every location, with spatial consistency being enforced by a novel regularizer that reduces curvature while preserving corners and junctions. The resulting 'field of junctions' is simultaneously a contour detector, corner/junction detector, and boundary-aware smoothing of regional appearance. Notably, its unified analysis of contours, corners, junctions and uniform regions allows it to succeed at high noise levels, where other methods for segmentation and boundary detection fail.

Related papers

• RecDiffusion: Rectangling for Image Stitching with Diffusion Models [53.824503710254206]
  We introduce a novel diffusion-based learning framework, textbfRecDiffusion, for image stitching rectangling. This framework combines Motion Diffusion Models (MDM) to generate motion fields, effectively transitioning from the stitched image's irregular borders to a geometrically corrected intermediary.
  arXiv  Detail & Related papers  (2024-03-28T06:22:45Z)
• CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks [10.622511683372815]
  We present CT-Bound, a robust and fast boundary detection method for very noisy images using a hybrid Convolution and Transformer neural network. During the local detection, the model uses a convolutional architecture to predict the boundary structure of each image patch. Then, it uses a feed-forward transformer architecture to globally refine the boundary structures of each patch to generate an edge map and a smoothed color map simultaneously.
  arXiv  Detail & Related papers  (2024-03-25T07:22:22Z)
• Boundary Attention: Learning curves, corners, junctions and grouping [23.467103272604906]
  We present a lightweight network that infers grouping and boundaries, including curves, corners and junctions. It operates in a bottom-up fashion, analogous to classical methods for sub-pixel edge localization and edge-linking. Our network uses a mechanism that we call boundary attention a geometry-aware local attention operation.
  arXiv  Detail & Related papers  (2024-01-01T19:00:55Z)
• Curvature from multipartite entanglement in quantum gravity states [0.0]
  We investigate the multipartite entanglement of a uniformly curved quantum 3D space region with boundary. We find three entanglement regimes depending on the ratio between the number of tags (curvature) and the area of the dual surface at the boundary.
  arXiv  Detail & Related papers  (2023-05-04T09:27:33Z)
• CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction [20.04081992616026]
  We present an enhanced corner representation method for structured reconstruction. It better reconstructs fine-grained structures, such as adjacent corners and tiny edges. It outperforms the state-of-the-art model by +1.9%@F-1 on Corner and +3.0%@F-1 on Edge.
  arXiv  Detail & Related papers  (2023-04-14T11:51:26Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• Think about boundary: Fusing multi-level boundary information for landmark heatmap regression [51.48533538153833]
  We study a two-stage but end-to-end approach for exploring the relationship between the facial boundary and landmarks. We get boundary-aware landmark predictions, which consists of two modules: the self-calibrated boundary estimation (SCBE) module and the boundary-aware landmark transform (BALT) module. Our approach outperforms state-of-the-art methods in the literature.
  arXiv  Detail & Related papers  (2020-08-25T10:14:13Z)
• Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement [19.309722425910465]
  We introduce a flexible interactive image segmentation model based on the Eikonal partial differential equation (PDE) framework. The proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.
  arXiv  Detail & Related papers  (2020-08-16T13:29:11Z)
• Hierarchical Verification for Adversarial Robustness [89.30150585592648]
  We introduce a new framework for the exact point-wise $ell_p$ robustness verification problem. LayerCert exploits the layer-wise geometric structure of deep feed-forward networks with rectified linear activations (ReLU networks) We show that LayerCert provably reduces the number and size of the convex programs that one needs to solve compared to GeoCert.
  arXiv  Detail & Related papers  (2020-07-23T07:03:05Z)
• Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization [99.96632216070718]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensional spatiality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. We propose a novel learning-based LF framework, in which each view of an LF image is first individually super-resolved.
  arXiv  Detail & Related papers  (2020-04-05T14:39:57Z)
• Saliency Enhancement using Gradient Domain Edges Merging [65.90255950853674]
  We develop a method to merge the edges with the saliency maps to improve the performance of the saliency. This leads to our proposed saliency enhancement using edges (SEE) with an average improvement of at least 3.4 times higher on the DUT-OMRON dataset. The SEE algorithm is split into 2 parts, SEE-Pre for preprocessing and SEE-Post pour postprocessing.
  arXiv  Detail & Related papers  (2020-02-11T14:04:56Z)

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.