论文标题
实时高光谱重建的MXR-U-NET
MXR-U-Nets for Real Time Hyperspectral Reconstruction
论文作者
论文摘要
最近，CNN对图像产生，超分辨率和样式转移的应用做出了重大贡献。在本文中，我们基于霍华德和古格的作品，他等人。 Misra，D。并提出了一个CNN体系结构，该体系结构可以准确地重建来自RGB对应物的高光谱图像。我们还提出了最佳模型的较浅版本，相对内存足迹和更快的推断速度为10％，从而实现了实时视频应用程序，同时仍然只有大约0.5％的性能下降。
In recent times, CNNs have made significant contributions to applications in image generation, super-resolution and style transfer. In this paper, we build upon the work of Howard and Gugger, He et al. and Misra, D. and propose a CNN architecture that accurately reconstructs hyperspectral images from their RGB counterparts. We also propose a much shallower version of our best model with a 10% relative memory footprint and 3x faster inference, thus enabling real-time video applications while still experiencing only about a 0.5% decrease in performance.
