Light Field Reconstruction using Hierarchical Features Fusion

Expert Systems with Applications(2020)

引用 11|浏览102
暂无评分
摘要
•U-Net can architecture to extract hierarchical features.•SAS can extract spatial and angular features for the 4D light field.•U-Net and SAS are combined into U-SAS-Net to take advantages of the two.•U-SAS-Net achieves 0.62 db better and 10x faster than state-of-the-art.•A large patch size is proved to be beneficial for learning the light field.
更多
查看译文
关键词
Light field,Deep learning,Neural network,Image processing
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要