论文标题
LHDR：使用轻质DNN的遗产内容重建HDR
LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN
论文作者
论文摘要
由于包含丰富的信息，高动态范围（HDR）图像在图形和摄影中被广泛使用。最近，该社区已开始使用深层神经网络（DNN）将标准动态范围（SDR）图像重建为HDR。尽管当前基于DNN的方法具有优势，但它们的应用程序方案仍然有限：（1）重型模型阻碍了实时处理，并且（2）对具有更多降级类型的Legacy SDR内容不适用。因此，我们提出了一种基于DNN的轻巧方法，该方法训练了解决Legacy SDR。为了更好地设计，我们改革问题建模并强调退化模型。实验表明，与其他方法相比，我们的方法以最低的计算成本达到了吸引人的性能。
High dynamic range (HDR) image is widely-used in graphics and photography due to the rich information it contains. Recently the community has started using deep neural network (DNN) to reconstruct standard dynamic range (SDR) images into HDR. Albeit the superiority of current DNN-based methods, their application scenario is still limited: (1) heavy model impedes real-time processing, and (2) inapplicable to legacy SDR content with more degradation types. Therefore, we propose a lightweight DNN-based method trained to tackle legacy SDR. For better design, we reform the problem modeling and emphasize degradation model. Experiments show that our method reached appealing performance with minimal computational cost compared with others.
