This letter introduces LYT-Net, a novel lightweight transformer-based model for low-light image enhancement. LYT-Net consists of several layers and detachable blocks, including our novel blocks-Channel-Wise Denoiser (CWD) and Multi-Stage Squeeze & Excite Fusion (MSEF)-along with the traditional Transformer block, Multi-Headed Self-Attention (MHSA). In our method we adopt a dual-path approach, treating chrominance channels $ U$ and $ V$ and luminance channel $ Y$ as separate entities to help the model better handle illumination adjustment and corruption restoration. Our comprehensive evaluation on established LLIE datasets demonstrates that, despite its low complexity, our model outperforms recent LLIE methods. The source code and pre-trained models are available at https://github.com/albrateanu/LYT-Net

Low-light image enhancement (LLIE) techniques improve the performance of image sensors by enhancing visibility and details in poorly lit environments and have significantly benefited from recent research into Transformer models. This work presents a novel Transformer attention mechanism inspired by the Kolmogorov–Arnold representation theorem, incorporating learnable non-linearity and multivariate function decomposition. This innovative mechanism is the foundation of KAN-$\mathcal{T}$, our proposed Transformer network. By enhancing feature flexibility and enabling the model to capture broader contextual information, KAN-$\mathcal{T}$ achieves superior performance. Our comprehensive experiments, both quantitative and qualitative, demonstrate that the proposed method achieves state-of-the-art performance in low-light image enhancement, highlighting its effectiveness and wide-ranging applicability. The code will be released upon publication.

Low-light image enhancement is an important task in computer vision, often made challenging by the limitations of image sensors, such as noise, low contrast, and color distortion. These challenges are further exacerbated by the computational demands of processing spatial dependencies under such conditions. We present a novel transformer-based framework that enhances efficiency by utilizing depthwise separable convolutions instead of conventional approaches. Additionally, an original feed-forward network design reduces the computational overhead while maintaining high performance. Experimental results demonstrate that this method achieves competitive results, providing a practical and effective solution for enhancing images captured in low-light environments.

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.

Low-light image enhancement (LLIE) is a fundamental yet challenging task due to the presence of noise, loss of detail, and poor contrast in images captured under insufficient lighting conditions. Recent methods often rely solely on pixel-level transformations of RGB images, neglecting the rich contextual information available from multiple visual modalities. In this paper, we present ModalFormer, the first large-scale multimodal framework for LLIE that fully exploits nine auxiliary modalities to achieve state-of-the-art performance. Our model comprises two main components: a Cross-modal Transformer (CM-T) designed to restore corrupted images while seamlessly integrating multimodal information, and multiple auxiliary subnetworks dedicated to multimodal feature reconstruction. Central to the CM-T is our novel Cross-modal Multi-headed Self-Attention mechanism (CM-MSA), which effectively fuses RGB data with modality-specific features--including deep feature embeddings, segmentation information, geometric cues, and color information--to generate information-rich hybrid attention maps. Extensive experiments on multiple benchmark datasets demonstrate ModalFormer's state-of-the-art performance in LLIE. Pre-trained models and results are made available at https://github.com/albrateanu/ModalFormer.