PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement
This addresses the challenge of robust image enhancement for machine and human vision in varied lighting without needing ground-truth data, though it is incremental as it builds on existing unsupervised approaches.
The paper tackles the problem of enhancing images under extreme lighting conditions, including both under- and over-exposure, by proposing an unsupervised framework that uses pseudo-ground-truth images from multiple source exposures, and it outperforms state-of-the-art unsupervised methods on public datasets.
The extremes of lighting (e.g. too much or too little light) usually cause many troubles for machine and human vision. Many recent works have mainly focused on under-exposure cases where images are often captured in low-light conditions (e.g. nighttime) and achieved promising results for enhancing the quality of images. However, they are inferior to handling images under over-exposure. To mitigate this limitation, we propose a novel unsupervised enhancement framework which is robust against various lighting conditions while does not require any well-exposed images to serve as the ground-truths. Our main concept is to construct pseudo-ground-truth images synthesized from multiple source images that simulate all potential exposure scenarios to train the enhancement network. Our extensive experiments show that the proposed approach consistently outperforms the current state-of-the-art unsupervised counterparts in several public datasets in terms of both quantitative metrics and qualitative results. Our code is available at https://github.com/VinAIResearch/PSENet-Image-Enhancement.