{"work":{"id":"2c2949fd-8a9e-4638-932c-944a5ab423b9","openalex_id":null,"doi":null,"arxiv_id":"1808.04560","raw_key":null,"title":"Deep Retinex Decomposition for Low-Light Enhancement","authors":null,"authors_text":"Chen Wei, Wenjing Wang, Wenhan Yang, and Jiaying Liu","year":2018,"venue":"cs.CV","abstract":"Retinex model is an effective tool for low-light image enhancement. It assumes that observed images can be decomposed into the reflectance and illumination. Most existing Retinex-based methods have carefully designed hand-crafted constraints and parameters for this highly ill-posed decomposition, which may be limited by model capacity when applied in various scenes. In this paper, we collect a LOw-Light dataset (LOL) containing low/normal-light image pairs and propose a deep Retinex-Net learned on this dataset, including a Decom-Net for decomposition and an Enhance-Net for illumination adjustment. In the training process for Decom-Net, there is no ground truth of decomposed reflectance and illumination. The network is learned with only key constraints including the consistent reflectance shared by paired low/normal-light images, and the smoothness of illumination. Based on the decomposition, subsequent lightness enhancement is conducted on illumination by an enhancement network called Enhance-Net, and for joint denoising there is a denoising operation on reflectance. The Retinex-Net is end-to-end trainable, so that the learned decomposition is by nature good for lightness adjustment. Extensive experiments demonstrate that our method not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.","external_url":"https://arxiv.org/abs/1808.04560","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-04T09:49:44.402408+00:00","pith_arxiv_id":"1808.04560","created_at":"2026-05-10T05:25:54.801553+00:00","updated_at":"2026-07-04T09:49:44.402408+00:00","title_quality_ok":true,"display_title":"Deep Retinex Decomposition for Low-Light Enhancement","render_title":"Deep Retinex Decomposition for Low-Light Enhancement"},"hub":{"state":{"work_id":"2c2949fd-8a9e-4638-932c-944a5ab423b9","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":51,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2025-04-03T08:06:24+00:00","last_pith_cited_at":"2026-07-01T23:26:26+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T10:39:34.232444+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":6},{"context_role":"background","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"use_dataset","n":6},{"context_polarity":"background","n":2},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}