Internal-External Boundary Attention Fusion for Glass Surface Segmentation

• URL: http://arxiv.org/abs/2307.00212v2
• Date: Mon, 4 Mar 2024 05:12:26 GMT
• Title: Internal-External Boundary Attention Fusion for Glass Surface Segmentation
• Authors: Dongshen Han and Seungkyu Lee and Chaoning Zhang and Heechan Yoon and Hyukmin Kwon and Hyun-Cheol Kim and Hyon-Gon Choo
• Abstract summary: We analytically investigate how glass surface boundary helps to characterize glass objects. Inspired by prior semantic segmentation approaches with challenging image types such as X-ray or CT scans, we propose separated internal-external boundary attention modules.
• Score: 14.335849624907611
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of other reflected or transmitted surfaces as well. Detecting glass regions from a single-color image is a challenging task. Recent deep-learning approaches have paid attention to the description of glass surface boundary where the transition of visual appearances between glass and non-glass surfaces are observed. In this work, we analytically investigate how glass surface boundary helps to characterize glass objects. Inspired by prior semantic segmentation approaches with challenging image types such as X-ray or CT scans, we propose separated internal-external boundary attention modules that individually learn and selectively integrate visual characteristics of the inside and outside region of glass surface from a single color image. Our proposed method is evaluated on six public benchmarks comparing with state-of-the-art methods showing promising results.

Related papers

• Glass Segmentation with Fusion of Learned and General Visual Features [2.3821941487858935]
  Glass surface segmentation from RGB images is a challenging task, since glass as a transparent material distinctly lacks visual characteristics.<n>This paper presents a novel architecture for glass segmentation, deploying a dual-backbone producing general visual features as well as task-specific learned visual features.<n>The architecture was evaluated on four commonly used glass segmentation datasets, achieving state-of-the-art results on several accuracy metrics.
  arXiv  Detail & Related papers  (2026-03-04T04:40:30Z)
• MVGD-Net: A Novel Motion-aware Video Glass Surface Detection Network [7.190998786246486]
  Glass surface ubiquitous in both daily life and professional environments presents a potential threat to vision-based systems.<n>We propose a novel network, named MVGD-Net, for detecting glass surfaces in videos by leveraging motion inconsistency cues.<n>For learning our network, we also propose a large-scale dataset, which comprises 312 diverse glass scenarios with a total of 19,268 frames.
  arXiv  Detail & Related papers  (2026-01-20T08:19:17Z)
• Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery [82.6332672749888]
  Glass surfaces are ubiquitous in daily life, typically appearing colorless, transparent, and lacking distinctive features.<n>We propose NFGlassNet, a novel method for glass surface detection that leverages the reflection dynamics present in flash/no-flash imagery.
  arXiv  Detail & Related papers  (2025-11-21T02:00:17Z)
• Fourier Boundary Features Network with Wider Catchers for Glass Segmentation [12.465008923418406]
  We propose a new method for constraining the segmentation of reflection surface and penetrating glass. The proposed method yields better segmentation performance compared with the state-of-the-art (SOTA) methods in glass image segmentation.
  arXiv  Detail & Related papers  (2024-05-15T15:52:27Z)
• Neural Radiance Fields for Transparent Object Using Visual Hull [0.8158530638728501]
  Recently introduced Neural Radiance Fields (NeRF) is a view synthesis method. We propose a NeRF-based method consisting of the following three steps: First, we reconstruct a three-dimensional shape of a transparent object using visual hull. Second, we simulate the refraction of the rays inside of the transparent object according to Snell's law. Last, we sample points through refracted rays and put them into NeRF.
  arXiv  Detail & Related papers  (2023-12-13T13:15:19Z)
• Curved Diffusion: A Generative Model With Optical Geometry Control [56.24220665691974]
  The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a textto-image diffusion model with the particular lens used in image rendering.
  arXiv  Detail & Related papers  (2023-11-29T13:06:48Z)
• Virtual Mirrors: Non-Line-of-Sight Imaging Beyond the Third Bounce [11.767522056116842]
  Non-line-of-sight (NLOS) imaging methods are capable of reconstructing complex scenes that are not visible to an observer using indirect illumination. We make the key observation that planar diffuse surfaces behave specularly at wavelengths used in the computational wave-based NLOS imaging domain. We leverage this observation to expand the capabilities of NLOS imaging using illumination beyond the third bounce.
  arXiv  Detail & Related papers  (2023-07-26T17:59:20Z)
• Periocular biometrics: databases, algorithms and directions [69.35569554213679]
  Periocular biometrics has been established as an independent modality due to concerns on the performance of iris or face systems in uncontrolled conditions. This paper presents a review of the state of the art in periocular biometric research.
  arXiv  Detail & Related papers  (2023-07-26T11:14:36Z)
• Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container [61.50401406132946]
  Transparent enclosures pose challenges of multiple light reflections and refractions at the interface between different propagation media. We use an existing neural reconstruction method (NeuS) that implicitly represents the geometry and appearance of the inner subspace. In order to account for complex light interactions, we develop a hybrid rendering strategy that combines volume rendering with ray tracing.
  arXiv  Detail & Related papers  (2023-03-24T04:58:27Z)
• MEGANE: Morphable Eyeglass and Avatar Network [83.65790119755053]
  We propose a 3D compositional morphable model of eyeglasses. We employ a hybrid representation that combines surface geometry and a volumetric representation. Our approach models global light transport effects, such as casting shadows between faces and glasses.
  arXiv  Detail & Related papers  (2023-02-09T18:59:49Z)
• Periocular Biometrics: A Modality for Unconstrained Scenarios [66.93179447621188]
  Periocular biometrics includes the externally visible region of the face that surrounds the eye socket. The COVID-19 pandemic has highlighted its importance, as the ocular region remained the only visible facial area even in controlled settings.
  arXiv  Detail & Related papers  (2022-12-28T12:08:27Z)
• Depth-aware Glass Surface Detection with Cross-modal Context Mining [39.091162729266294]
  Glass surfaces are becoming increasingly ubiquitous as modern buildings tend to use a lot of glass panels. This poses substantial challenges on the operations of autonomous systems such as robots, self-driving cars and drones. Existing works attempt to exploit various cues, including glass boundary context or reflections, as a prior. We propose a novel framework for glass surface detection by incorporating RGB-D information.
  arXiv  Detail & Related papers  (2022-06-22T17:56:09Z)
• Visual Vibration Tomography: Estimating Interior Material Properties from Monocular Video [66.94502090429806]
  An object's interior material properties, while invisible to the human eye, determine motion observed on its surface. We propose an approach that estimates heterogeneous material properties of an object from a monocular video of its surface vibrations.
  arXiv  Detail & Related papers  (2021-04-06T18:05:27Z)
• Refractive Light-Field Features for Curved Transparent Objects in Structure from Motion [10.380414189465345]
  We propose a novel image feature for light fields that detects and describes the patterns of light refracted through curved transparent objects. We demonstrate improved structure-from-motion performance in challenging scenes containing refractive objects. Our method is a critical step towards allowing robots to operate around refractive objects.
  arXiv  Detail & Related papers  (2021-03-29T05:55:32Z)

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.