RetinexGAN Enables More Robust Low-Light Image Enhancement Via Retinex Decomposition Based Unsupervised Illumination Brightening
Primary Area: representation learning for computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: low-light image enhancement, Retinex decomposition, feature pyramid network (FPN), attention mechanism, unsupervised illumination brightening
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: Most existing image enhancement techniques rely heavily on strict supervision of paired images. Moreover, unsupervised enhancement methods also face challenges in achieving a balance between model performance and efficiency when handling real-world low-light images in unknown complex scenarios. Herein, we present a novel low-light image enhancement scheme termed \textbf{RetinexGAN} that can leverage the supervision of a limited number of low-light/normal image pairs to realize an accurate Retinex decomposition, and based on this, achieve brightening the illumination of unpaired images to reduce dependence on paired datasets and improve generalization ability. The decomposition network is learned with some newly established constraints for complete decoupling between reflectance and illumination. For the first time, we introduce the feature pyramid network (FPN) to adjust the illumination maps of other low-light images without any supervision. Under this flexible framework, a wide range of backbones can be employed to work with illumination map generator, to navigate the balance between performance and efficiency. In addition, a novel attention mechanism is integrated into the FPN for giving the adaptability towards application scenes with different environment like underwater image enhancement (UIE) and dark face detection. Extensive experiments demonstrate that our proposed scheme has a more robust performance with high efficiency facing various images from different low-light environments over state-of-the-art methods.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 190
Loading