{"ID":562804,"CreatedAt":"2026-03-04T20:59:09Z","UpdatedAt":"2026-03-04T20:59:09Z","DeletedAt":null,"paper_url":"https://paperswithcode.com/paper/reco-diff-explore-retinex-based-condition","arxiv_id":"2312.12826","title":"JoReS-Diff: Joint Retinex and Semantic Priors in Diffusion Model for Low-light Image Enhancement","abstract":"Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models. Despite the success of some conditional methods, previous methods may neglect the importance of a sufficient formulation of task-specific condition strategy, resulting in suboptimal visual outcomes. In this study, we propose JoReS-Diff, a novel approach that incorporates Retinex- and semantic-based priors as the additional pre-processing condition to regulate the generating capabilities of the diffusion model. We first leverage pre-trained decomposition network to generate the Retinex prior, which is updated with better quality by an adjustment network and integrated into a refinement network to implement Retinex-based conditional generation at both feature- and image-levels. Moreover, the semantic prior is extracted from the input image with an off-the-shelf semantic segmentation model and incorporated through semantic attention layers. By treating Retinex- and semantic-based priors as the condition, JoReS-Diff presents a unique perspective for establishing an diffusion model for LLIE and similar image enhancement tasks. Extensive experiments validate the rationality and superiority of our approach.","url_abs":"https://arxiv.org/abs/2312.12826v2","url_pdf":"https://arxiv.org/pdf/2312.12826v2.pdf","authors":"[\"Yuhui Wu\", \"Guoqing Wang\", \"Zhiwen Wang\", \"Yang Yang\", \"Tianyu Li\", \"Malu Zhang\", \"Chongyi Li\", \"Heng Tao Shen\"]","published":"2023-12-20T00:00:00Z","tasks":"[\"Image Enhancement\", \"Low-Light Image Enhancement\", \"Semantic Segmentation\"]","methods":"[\"Diffusion\"]","has_code":false}