{"ID":2878513,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17885","arxiv_id":"2508.17885","title":"ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement","abstract":"We introduce ISALux, a novel transformer-based approach for Low-Light Image Enhancement (LLIE) that seamlessly integrates illumination and semantic priors. Our architecture includes an original self-attention block, Hybrid Illumination and Semantics-Aware Multi-Headed Self- Attention (HISA-MSA), which integrates illumination and semantic segmentation maps for en- hanced feature extraction. ISALux employs two self-attention modules to independently process illumination and semantic features, selectively enriching each other to regulate luminance and high- light structural variations in real-world scenarios. A Mixture of Experts (MoE)-based Feed-Forward Network (FFN) enhances contextual learning, with a gating mechanism conditionally activating the top K experts for specialized processing. To address overfitting in LLIE methods caused by distinct light patterns in benchmarking datasets, we enhance the HISA-MSA module with low-rank matrix adaptations (LoRA). Extensive qualitative and quantitative evaluations across multiple specialized datasets demonstrate that ISALux is competitive with state-of-the-art (SOTA) methods. Addition- ally, an ablation study highlights the contribution of each component in the proposed model. Code will be released upon publication.","short_abstract":"We introduce ISALux, a novel transformer-based approach for Low-Light Image Enhancement (LLIE) that seamlessly integrates illumination and semantic priors. Our architecture includes an original self-attention block, Hybrid Illumination and Semantics-Aware Multi-Headed Self- Attention (HISA-MSA), which integrates illumi...","url_abs":"https://arxiv.org/abs/2508.17885","url_pdf":"https://arxiv.org/pdf/2508.17885v1","authors":"[\"Raul Balmez\",\"Alexandru Brateanu\",\"Ciprian Orhei\",\"Codruta Ancuti\",\"Cosmin Ancuti\"]","published":"2025-08-25T10:47:18Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Mixture of Experts\",\"Transformer\",\"LoRA\"]","has_code":false}