用参考图指导曝光校正，让照片亮度更自然。
Learning Reference-Guided Exposure Correction with Hybrid Illumination Characteristics
- 用轻量编码器提取光照特征，对比源图与参考图的差异
- 多尺度调制网络实现精细的光影自适应调整
- 无需真实标签也能跨场景泛化，适合真实拍摄场景
我们提出HICNet，一种基于参考图的曝光校正框架。一个轻量、内容无关的编码器将每张图像压缩为紧凑的光照嵌入，捕捉区域亮度、边缘对比度及高阶亮度矩。源图与参考图之间的嵌入差异驱动一个多尺度调制网络，结合FiLM全局调节与光度通道重平衡，实现细粒度、光照感知的谱域门控，生成曝光一致且保留场景细节的输出。采用跨批次对比损失对光照流形进行排序，增强对多样光照条件的鲁棒性。训练无需真实标签或固有分解，已在公开基准上取得更优精度，并能良好泛化至完全未见过的场景。
原文摘要 · Abstract (English)
We present HICNet, a reference-guided exposure correction framework. A lightweight, content-agnostic encoder distills each image into a compact illumination embedding capturing regional brightness, edge contrast, and higher-order luminance moments. The embedding difference between a source and its reference drives a multi-scale modulation network that combines FiLM-based global adjustment with Photometric Channel Rebalancing for fine-grained, illumination-aware spectral gating, producing exposure-matched outputs while faithfully preserving scene details. A cross-batch contrastive loss orders the illumination manifold, bolstering robustness to diverse lighting conditions. Trained without ground truth or intrinsic decomposition, HICNet attains better accuracy on public benchmarks and generalizes well to entirely unseen scenes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。