The climate change issue has become a growing concern due to the increasing greenhouse gas emissions. To achieve carbon neutrality for mitigating the climate problem, the oxy-fuel combustion (OFC) technique on internal combustion engines (ICEs) has attracted much attention. Furthermore, the water injection (WI) strategy was proven effective in improving the combustion process and thermal efficiency in engines under OFC mode. However, WI strategy effects on gasoline direct injection (GDI) engines fuelled with gasoline–alcohol blends have not been reported. This study quantitatively analysed WI mass and timing effects on oxy-fuel combustion performance from a GDI engine fuelled with E10 (10% ethanol and 90% gasoline in mass) by simulation. The results show that equivalent brake-specific fuel consumption (BSFCE) shows a monotonically decreasing trend with the increase in the water–fuel mass ratio () from 0 to 0.2. However, further increasing would cause a deterioration in BSFCE due to the enhanced cooling effects of water vaporisation. Moreover, an appropriate water injection timing () could be explored for improving OFC performance, especially for large conditions. The difference in BSFCE between = −100°CA and = −60°CA can be up to around 6.3 g/kWh by increasing to 0.6.
Learning and improving large language models through human preference feedback has become a mainstream approach, but it has rarely been applied to the field of low-light image enhancement. Existing low-light enhancement evaluations typically rely on objective metrics (such as FID, PSNR, etc.), which often result in models that perform well objectively but lack aesthetic quality. Moreover, most low-light enhancement models are primarily designed for global brightening, lacking detailed refinement. Therefore, the generated images often require additional local adjustments, leading to research gaps in practical applications. To bridge this gap, we propose the following innovations: 1) We collect human aesthetic evaluation text pairs and aesthetic scores from multiple low-light image datasets (e.g., LOL, LOL2, LOM, DCIM, MEF, etc.) to train a low-light image aesthetic evaluation model, supplemented by an optimization algorithm designed to fine-tune the diffusion model. 2) We propose a prompt-driven brightness adjustment module capable of performing fine-grained brightness and aesthetic adjustments for specific instances or regions. 3) We evaluate our method alongside existing state-of-the-art algorithms on mainstream benchmarks. Experimental results show that our method not only outperforms traditional methods in terms of visual quality but also provides greater flexibility and controllability, paving the way for improved aesthetic quality.
Images captured under low-light conditions are often plagued by several challenges, including diminished contrast, increased noise, loss of fine details, and unnatural color reproduction. These factors can significantly hinder the performance of computer vision tasks such as object detection and image segmentation. As a result, improving the quality of low-light images is of paramount importance for practical applications in the computer vision domain.To effectively address these challenges, we present a novel low-light image enhancement model, termed Spatial Consistency Retinex Network (SCRNet), which leverages the Retinex-based structure and is guided by the principle of spatial consistency.Specifically, our proposed model incorporates three levels of consistency: channel level, semantic level, and texture level, inspired by the principle of spatial consistency.These levels of consistency enable our model to adaptively enhance image features, ensuring more accurate and visually pleasing results.Extensive experimental evaluations on various low-light image datasets demonstrate that our proposed SCRNet outshines existing state-of-the-art methods, highlighting the potential of SCRNet as an effective solution for enhancing low-light images.