LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN
This work addresses the limited application of existing DNN-based HDR reconstruction methods for legacy content, offering a more efficient solution for graphics and photography domains.
The paper tackled the problem of reconstructing high dynamic range (HDR) images from legacy standard dynamic range (SDR) content with degradation, proposing a lightweight deep neural network (DNN) method that achieved appealing performance with minimal computational cost compared to others.
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.