2023AAAI_Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method(LLformer)

一. motivition

1. 之前的数据集分辨率较低

二. contribution

1. 提出两个超高清数据集UHD-4k和UHD-8k

2. 网络结构LLFormer(网络结构类似2022CVPR_Restormer: Effificient Transformer forHigh-Resolution Image Restoration.)

三. Network

 网络架构类似于：2022CVPR_Restormer: Effificient Transformer for High-Resolution Image Restoration 的网络结构：

四. Loss

本栏目推荐文章
• LLM series: Transformer
• Learning Dynamic Query Combinations for Transformer-based Object** Detection and Segmentation论文阅读笔记
• [NLP复习笔记] Transformer
• RNN 和 Transformer 复杂度比较
• 挑战Transformer的新架构Mamba解析以及Pytorch复现
• 《Span-Based Joint Entity and Relation Extraction with Transformer Pre-Training》阅读笔记
• ICLR 2022: Anomaly Transformer论文阅读笔记+代码复现
• Visual Transformer 与归纳偏置
• Swin Transformer
• VIT Vision Transformer