Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...

You might also read

Related Articles

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

Sort by

Same author

Random subspace-based ensemble classifier for high-dimensional data Using SPARK.

PloS one·2026

Same author

Modeling LTE-advanced cell capacity estimation using packet bundling and carrier aggregation.

PeerJ. Computer science·2025

Same author

Development of bile duct bezoars following cholecystectomy caused by choledochocolonic fistula formation.

Annals of gastroenterology·2014

Same author

Hepatic pulmonary fusion: a rare association of right-sided congenital diaphragmatic hernia.

Annals of gastroenterology·2014

Same author

Spatial distribution of persistent organic pollutants in the surface water of River Brahmaputra and River Ganga in India.

Reviews on environmental health·2014

Same author

Three-dimensional patterning of multiple cell populations through orthogonal genetic control of cell motility.

Soft matter·2014

Search research articles

Related Experiment Video

Updated: Apr 29, 2026

High-resolution Single Particle Analysis from Electron Cryo-microscopy Images Using SPHIRE

High-resolution Single Particle Analysis from Electron Cryo-microscopy Images Using SPHIRE

Published on: May 16, 2017

ShadowFormer++: multi-scale shadow priors and diffusion-guided refinement for high-fidelity shadow removal.

Stutee Mohanty¹, Sanjay Kumar¹, Rajiv Senapati²

¹Department of Computer Science and Engineering, SRM University-AP, Amaravati, Andhra Pradesh, 522 240, India.

Scientific Reports

|April 27, 2026

Summary

ShadowFormer++ efficiently removes image shadows using a transformer and diffusion model. This novel approach improves object detection and image quality for real-time computer vision applications.

Keywords:

Computer vision Deep learning Image enhancement Image processing Shadow removal

More Related Videos

High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

Published on: October 28, 2025

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

Published on: June 23, 2023

Related Experiment Videos

Last Updated: Apr 29, 2026

High-resolution Single Particle Analysis from Electron Cryo-microscopy Images Using SPHIRE

High-resolution Single Particle Analysis from Electron Cryo-microscopy Images Using SPHIRE

Published on: May 16, 2017

High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

Published on: October 28, 2025

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

Published on: June 23, 2023

Area of Science:

Computer Vision
Image Processing
Artificial Intelligence

Background:

Image shadows degrade quality, hindering computer vision tasks like object detection and segmentation.
Current shadow removal methods struggle with accurate localization, texture preservation, and computational efficiency.

Purpose of the Study:

To propose ShadowFormer++, a novel framework for efficient and high-quality shadow removal.
To address limitations of existing methods in accuracy, texture detail, and computational cost.

Main Methods:

Developed ShadowFormer++, integrating a transformer and diffusion model.
Incorporated Multi-Scale Local Shadow Perception Module (MS-LSPM) for local feature extraction.
Utilized Shadow-Aware Transformer Encoder (SATE) for global context and Diffusion-Inspired Refinement Module (DIRM) for reconstruction.

Main Results:

Achieved Mean Absolute Error (MAE) of 3.79, Peak Signal-to-Noise Ratio (PSNR) of 33.58 dB, and Structural Similarity Index (SSIM) of 0.972.
Outperformed state-of-the-art methods including ShadowFormer, SpA-Former, and Diff-Shadow on ISTD, ISTD+, and SRD datasets.
Demonstrated a balance between computational efficiency and superior shadow removal quality.

Conclusions:

ShadowFormer++ offers an effective solution for shadow removal in computer vision.
The framework's efficiency and quality make it suitable for real-time applications.
Enables advancements in robotics, autonomous systems, and augmented reality.