Despite recent strides made by AI in image processing, the issue of mixed exposure, pivotal in many real-world scenarios like surveillance and photography, remains inadequately addressed. Traditional image enhancement techniques and current transformer models are limited with primary focus on either overexposure or underexposure. To bridge this gap, we introduce the Unified-Exposure Guided Transformer (Unified-EGformer). Our proposed solution is built upon advanced transformer architectures, equipped with local pixel-level refinement and global refinement blocks for color correction and image-wide adjustments. We employ a guided attention mechanism to precisely identify exposure-compromised regions, ensuring its adaptability across various real-world conditions. U-EGformer, with a lightweight design featuring a memory footprint (peak memory) of only $\sim$1134 MB (0.1 Million parameters) and an inference time of 95 ms (9.61x faster than the average), is a viable choice for real-time applications such as surveillance and autonomous navigation. Additionally, our model is highly generalizable, requiring minimal fine-tuning to handle multiple tasks and datasets with a single architecture.

翻译：尽管人工智能在图像处理领域取得了最新进展，但混合曝光问题——在监控和摄影等众多现实场景中至关重要——仍未得到充分解决。传统图像增强技术与当前Transformer模型主要局限于仅关注过曝光或欠曝光。为弥补这一不足，我们提出了统一曝光引导Transformer（Unified-EGformer）。我们提出的解决方案基于先进的Transformer架构，配备了局部像素级细化模块和全局细化模块，用于色彩校正与全图调整。我们采用引导注意力机制来精确识别曝光受损区域，确保其在不同现实条件下的适应性。U-EGformer采用轻量化设计，其内存占用量（峰值内存）仅为$\sim$1134 MB（参数量0.1百万），推理时间95毫秒（比平均水平快9.61倍），是监控和自主导航等实时应用的可行选择。此外，我们的模型具有高度泛化能力，仅需极少量微调即可通过单一架构处理多任务与多数据集。