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

Confocal Fluorescence Microscopy01:16

Confocal Fluorescence Microscopy

13.0K
Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...
13.0K

You might also read

Related Articles

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

Sort by
Same author

Chemotherapy combined with immunotherapy vs. chemotherapy: comparison of safety and efficacy in adjuvant therapy for intrahepatic cholangiocarcinoma.

Frontiers in oncology·2026
Same author

Behind the screen: Unraveling the role of perceived closeness difference in shaping viewers' engagement behaviors.

PloS one·2026
Same author

Multi-omics profiling-derived signature links cellular ecosystem to glioblastoma prognosis.

iScience·2026
Same author

Laparoscopic right caudate lobectomy combined with right posterior lobectomy for hepatocellular carcinoma after neoadjuvant therapy (with video).

Surgical oncology·2026
Same author

Anchor-induced localized stress evolution and deformation prediction in SOI MEMS structures.

Microsystems & nanoengineering·2026
Same author

Thermo-Bistable Red and Sensitized Near-Infrared Photoswitches.

Journal of the American Chemical Society·2026

Related Experiment Video

Updated: May 28, 2025

Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function
11:35

Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function

Published on: December 8, 2010

16.5K

DCLTV: An Improved Dual-Condition Diffusion Model for Laser-Visible Image Translation.

Xiaoyu Zhang1, Laixian Zhang2,3, Huichao Guo2,3

  • 1Graduate School, Space Engineering University, Beijing 101416, China.

Sensors (Basel, Switzerland)
|February 13, 2025
PubMed
Summary

This study introduces DCLTV, a novel dual-condition controlled diffusion model for translating laser images to visible images. DCLTV overcomes limitations of existing methods, achieving superior image quality and accuracy in cross-modal translation.

Keywords:
Brownian bridgediffusion modelimage translationlaser images

More Related Videos

Live Images of GLUT4 Protein Trafficking in Mouse Primary Hypothalamic Neurons Using Deconvolution Microscopy
08:47

Live Images of GLUT4 Protein Trafficking in Mouse Primary Hypothalamic Neurons Using Deconvolution Microscopy

Published on: December 7, 2017

9.6K
Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture
09:04

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Published on: February 23, 2018

9.4K

Related Experiment Videos

Last Updated: May 28, 2025

Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function
11:35

Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function

Published on: December 8, 2010

16.5K
Live Images of GLUT4 Protein Trafficking in Mouse Primary Hypothalamic Neurons Using Deconvolution Microscopy
08:47

Live Images of GLUT4 Protein Trafficking in Mouse Primary Hypothalamic Neurons Using Deconvolution Microscopy

Published on: December 7, 2017

9.6K
Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture
09:04

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Published on: February 23, 2018

9.4K

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Laser active imaging offers clear images in difficult conditions, unlike visible light systems.
  • Laser images have modal discrepancies hindering perception and processing, necessitating cross-modal translation.
  • Existing translation methods struggle with training complexity and color bleeding.

Purpose of the Study:

  • To develop an advanced diffusion model for accurate laser-to-visible image translation.
  • To address the limitations of current cross-modal image translation algorithms.
  • To improve human perception and computer processing of laser imaging data.

Main Methods:

  • Designed DCLTV, an improved diffusion model with dual-condition control.
  • Incorporated Brownian bridge strategy for the first condition control.
  • Utilized interpolation-based conditional injection for the second condition control.
  • Created a new dataset of 665 laser-visible image pairs.

Main Results:

  • DCLTV outperformed five baseline models (Pix2pix, BigColor, CT2, ColorFormer, DDColor).
  • Achieved at least a 15.89% reduction in Fréchet Inception Distance (FID) and 22.02% in Learned Perceptual Image Patch Similarity (LPIPS).
  • Ablation experiments confirmed the effectiveness of dual conditions, yielding FID of 154.74 and LPIPS of 0.379.

Conclusions:

  • DCLTV demonstrates superior performance in laser-to-visible image translation.
  • The dual-condition control mechanism effectively enhances translation accuracy and image quality.
  • The developed dataset addresses data scarcity in this specialized imaging field.