Boundary Attention: Learning to Localize Boundaries under High Noise

• URL: http://arxiv.org/abs/2401.00935v2
• Date: Mon, 18 Mar 2024 23:41:41 GMT
• Title: Boundary Attention: Learning to Localize Boundaries under High Noise
• Authors: Mia Gaia Polansky, Charles Herrmann, Junhwa Hur, Deqing Sun, Dor Verbin, Todd Zickler,
• Abstract summary: We present a differentiable model that infers explicit boundaries, including curves, corners and junctions, using a mechanism that we call boundary attention. Boundary attention is a boundary-aware local attention operation that, when applied densely and repeatedly, progressively refines a field of variables. We find that our method generalizes to natural images corrupted by real sensor noise, and predicts consistent boundaries under increasingly noisy conditions.
• Score: 23.467103272604906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a differentiable model that infers explicit boundaries, including curves, corners and junctions, using a mechanism that we call boundary attention. Boundary attention is a boundary-aware local attention operation that, when applied densely and repeatedly, progressively refines a field of variables that specify an unrasterized description of the local boundary structure in every overlapping patch within an image. It operates in a bottom-up fashion, similar to classical methods for sub-pixel edge localization and edge-linking, but with a higher-dimensional description of local boundary structure, a notion of spatial consistency that is learned instead of designed, and a sequence of operations that is end-to-end differentiable. We train our model using simple synthetic data and then evaluate it using photographs that were captured under low-light conditions with variable amounts of noise. We find that our method generalizes to natural images corrupted by real sensor noise, and predicts consistent boundaries under increasingly noisy conditions where other state-of-the-art methods fail.

Related papers

• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds [20.484401728812376]
  We introduce STAR-Edge, a novel approach for detecting and refining edge points in thin-walled structures. Our method leverages a unique representation-the local spherical curve-to create structure-aware neighborhoods. Experiments conducted on the ABC dataset and thin-walled structure-specific datasets demonstrate that STAR-Edge outperforms existing edge detection methods.
  arXiv  Detail & Related papers  (2025-03-02T08:51:13Z)
• Generating grid maps via the snake model [10.489493860187348]
  The grid map, often referred to as the tile map, stands as a vital tool in geospatial visualization. It transforms geographic regions into grids, which requires the displacement of both region centroids and boundary nodes to establish a coherent grid arrangement. Existing approaches typically displace region centroids and boundary nodes separately, potentially resulting in self-intersected boundaries. We introduce a novel approach that leverages the Snake displacement algorithm from cartographic generalization to concurrently displace region centroids and boundary nodes.
  arXiv  Detail & Related papers  (2024-06-04T02:24:39Z)
• Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis [70.40950409274312]
  We modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. We also develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices.
  arXiv  Detail & Related papers  (2024-02-19T18:59:41Z)
• DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning [12.047523258256088]
  We introduce DeepBranchTracer, a novel method that learns both external image features and internal geometric characteristics to reconstruct curvilinear structures. We extensively evaluated our model on both 2D and 3D datasets, demonstrating its superior performance over existing segmentation and reconstruction methods.
  arXiv  Detail & Related papers  (2024-02-02T07:13:07Z)
• Parallax-Tolerant Unsupervised Deep Image Stitching [57.76737888499145]
  We propose UDIS++, a parallax-tolerant unsupervised deep image stitching technique. First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion. To further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks.
  arXiv  Detail & Related papers  (2023-02-16T10:40:55Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Neural Convolutional Surfaces [59.172308741945336]
  This work is concerned with a representation of shapes that disentangles fine, local and possibly repeating geometry, from global, coarse structures. We show that this approach achieves better neural shape compression than the state of the art, as well as enabling manipulation and transfer of shape details.
  arXiv  Detail & Related papers  (2022-04-05T15:40:11Z)
• DeepCurrents: Learning Implicit Representations of Shapes with Boundaries [25.317812435426216]
  We propose a hybrid shape representation that combines explicit boundary curves with implicit learned interiors. We further demonstrate learning families of shapes jointly parameterized by boundary curves and latent codes.
  arXiv  Detail & Related papers  (2021-11-17T20:34:20Z)
• Field of Junctions: Extracting Boundary Structure at Low SNR [5.584060970507507]
  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.
  arXiv  Detail & Related papers  (2020-11-27T17:46:08Z)
• Neural Subdivision [58.97214948753937]
  This paper introduces Neural Subdivision, a novel framework for data-driven coarseto-fine geometry modeling. We optimize for the same set of network weights across all local mesh patches, thus providing an architecture that is not constrained to a specific input mesh, fixed genus, or category. We demonstrate that even when trained on a single high-resolution mesh our method generates reasonable subdivisions for novel shapes.
  arXiv  Detail & Related papers  (2020-05-04T20:03:21Z)
• Multi-View Optimization of Local Feature Geometry [70.18863787469805]
  We address the problem of refining the geometry of local image features from multiple views without known scene or camera geometry. Our proposed method naturally complements the traditional feature extraction and matching paradigm. We show that our method consistently improves the triangulation and camera localization performance for both hand-crafted and learned local features.
  arXiv  Detail & Related papers  (2020-03-18T17:22:11Z)

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.