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 Experiment Videos

High dynamic range image rendering with a Retinex-based adaptive filter.

Laurence Meylan1, Sabine Süsstrunk

  • 1School of Computer and Communication Sciences, Ecole Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|September 5, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Discovering Partial Differential Equations With Neural Cellular Automata.

Artificial life·2026
Same author

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Fast Adversarial Training With Adaptive Step Size.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

BIGPrior: Toward Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

Training Provably Robust Models by Polyhedral Envelope Regularization.

IEEE transactions on neural networks and learning systems·2021
Same author

Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2020
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

This study introduces a novel high dynamic range (HDR) image rendering method. It effectively reduces artifacts by adapting to human visual perception and image edges.

Area of Science:

  • Computer Vision
  • Image Processing
  • Human Visual System Modeling

Background:

  • High dynamic range (HDR) imaging aims to represent a greater range of luminance than standard displays.
  • Existing methods often struggle with artifacts like halos due to limitations in modeling visual adaptation.
  • Human visual system (HVS) adaptation plays a crucial role in perceiving luminance and color.

Purpose of the Study:

  • To develop an advanced method for rendering high dynamic range images.
  • To improve upon current state-of-the-art techniques by reducing common rendering artifacts.
  • To incorporate global and local adaptation principles of the human visual system into image rendering.

Main Methods:

  • The proposed method is based on the center-surround Retinex model.

Related Experiment Videos

  • An adaptive filter is employed, conforming to image high-contrast edges to minimize halo artifacts.
  • Processing is restricted to the luminance channel, identified via principal component analysis (PCA) for channel orthogonality.

    • Main Results:

    • The method successfully renders high dynamic range images with reduced artifacts.
    • Principal component analysis (PCA) effectively isolates the luminance channel, minimizing unwanted chromatic shifts.
    • The adaptive filter significantly mitigates halo artifacts prevalent in other HDR rendering techniques.

    Conclusions:

    • The novel center-surround Retinex-based method offers efficient and artifact-reduced HDR image rendering.
    • By modeling HVS adaptation and using edge-aware filtering, the technique enhances visual quality.
    • The approach demonstrates superior performance compared to existing state-of-the-art methods.