Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

1.8K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
1.8K
Parallel Processing01:20

Parallel Processing

637
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
637

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Magnetic Biochar Prepared with <i>Rosa roxburghii</i> Residue as Adsorbents for Congo Red Removal.

Materials (Basel, Switzerland)·2025
Same author

Spatial Regulation of Cancer-Associated Fibroblasts and Tumor Cells via pH-Responsive Bispecific Antibody Delivery for Enhanced Chemo-Immunotherapy Synergy.

ACS nano·2025
Same author

Ru Single Atoms Anchored on Oxygen-Vacancy-Rich ZrO<sub>2-x</sub>/C for Synergistically Enhanced Hydrogen Oxidation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

A single-dose, four-cycle, fully repetitive crossover bioequivalence of dabigatran etexilate in Chinese.

BMC pharmacology & toxicology·2025
Same author

Lattice-Confined Ru Electrocatalysts with Optimal Localized Interfacial Electrons for Efficient Alkaline Hydrogen Oxidation.

Nano letters·2025
Same author

DGK1 as a Target of Gemfibrozil to Induce Lipid Accumulation via the Transcription Factors TUP1/CYC8 in Saccharomyces cerevisiae.

Journal of basic microbiology·2025

Related Experiment Video

Updated: Jan 16, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Multi-dimensional perception-guided iterative reflection removal network with deep features for painting images.

Yuqi Xie1,2, Xiaojuan Zhang3,4, Yang Zhao5

  • 1School of Computer Science, Qinghai Normal University, Xining, 810016, China.

Scientific Reports
|September 29, 2025
PubMed
Summary

This study introduces MPGINet, an iterative network for removing glass cover reflections from digitized Thangka paintings. The novel approach significantly improves image quality, preserving artwork details.

Keywords:
Deep feature pyramid networkMulti-dimensional feature fusionRegong ThangkaSingle image reflection removal

More Related Videos

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Related Experiment Videos

Last Updated: Jan 16, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Computer Vision
  • Digital Image Processing
  • Art Conservation Technology

Background:

  • Digitizing Thangka paintings is hindered by image quality degradation due to glass cover reflections.
  • Existing methods struggle to effectively remove these reflections without compromising artwork details.

Purpose of the Study:

  • To develop an innovative iterative prediction network (MPGINet) for robust reflection removal in Thangka painting digitization.
  • To enhance the visual fidelity of digitized artworks by addressing reflection-induced artifacts.

Main Methods:

  • Proposed an iterative prediction network (MPGINet) utilizing multi-dimensional deep features and reflection perception.
  • Employed a two-stage architecture: U-Net with Squeeze-and-Excitation for reflection layer refinement and Deep Feature Pyramid Network (DFPN) for transmission layer restoration.
  • Integrated frequency-domain information separation and mask-guided image inpainting for enhanced reflection removal.

Main Results:

  • MPGINet achieved PSNR of 28.90 dB and SSIM of 0.962 on Thangka datasets, outperforming state-of-the-art (SOTA) methods by 1.88 dB and 0.027.
  • Demonstrated generalization ability on natural scene datasets, achieving comparable results with SOTA methods.

Conclusions:

  • MPGINet effectively removes glass cover reflections, significantly improving image quality for digitized Thangka paintings.
  • The network's architecture, combining deep feature fusion and iterative refinement, ensures detailed restoration and preserves artwork authenticity.