{"ID":2844679,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06066","arxiv_id":"2511.06066","title":"LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction","abstract":"Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are difficult to obtain in practical scenarios. To address this limitation, we propose a pseudo label-based unsupervised method called LoopExpose for arbitrary-length exposure correction. A nested loop optimization strategy is proposed to address the exposure correction problem, where the correction model and pseudo-supervised information are jointly optimized in a two-level framework. Specifically, the upper-level trains a correction model using pseudo-labels generated through multi-exposure fusion at the lower level. A feedback mechanism is introduced where corrected images are fed back into the fusion process to refine the pseudo-labels, creating a self-reinforcing learning loop. Considering the dominant role of luminance calibration in exposure correction, a Luminance Ranking Loss is introduced to leverage the relative luminance ordering across the input sequence as a self-supervised constraint. Extensive experiments on different benchmark datasets demonstrate that LoopExpose achieves superior exposure correction and fusion performance, outperforming existing state-of-the-art unsupervised methods. Code is available at https://github.com/FALALAS/LoopExpose.","short_abstract":"Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are difficult to obtain in practical scenarios. To address this limitation, we propose a...","url_abs":"https://arxiv.org/abs/2511.06066","url_pdf":"https://arxiv.org/pdf/2511.06066v1","authors":"[\"Ao Li\",\"Chen Chen\",\"Zhenyu Wang\",\"Tao Huang\",\"Fangfang Wu\",\"Weisheng Dong\"]","published":"2025-11-08T16:36:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607316,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2844679,"paper_url":"https://arxiv.org/abs/2511.06066","paper_title":"LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction","repo_url":"https://github.com/FALALAS/LoopExpose","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}