Bifurcated convolutional network for Specular Highlight Removal
DOI:
Author:
Affiliation:

1.Zhejiang University of Technology;2.College of Computer Science and Technology, Zhejiang University of Technology

Clc Number:

Fund Project:

The National Key Technologies R&D Program of China

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Specular highlight usually causes serious information degradation, which leads to the failure of many computer vision algorithms. We have proposed a novel bifurcated convolution neural network (Bifurcated-CNN) to tackle the problem of high reflectivity image information degradation. 1) The specular highlight features are extracted and removed in two stages from coarse to fine, to ensure the generation of diffuse images have no visual artifacts and information distortions. 2) A bifurcated feature selection strategy (BFSS) is designed to filter out the specular highlight features and enhance the detection capability of our network. The experiments on two types of challenging datasets demonstrate that our method outperforms state-of-the-art approaches for specular highlight detection and removal. The effectiveness of the proposed BFSS and Bifurcated-CNN are also verified.

    Reference
    Related
    Cited by
Get Citation
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:February 20,2023
  • Revised:April 06,2023
  • Adopted:April 26,2023
  • Online:
  • Published: