论文标题
SDRTV-TO-HDRTV通过时空特征融合转换
SDRTV-to-HDRTV Conversion via Spatial-Temporal Feature Fusion
论文作者
论文摘要
HDR（高动态范围）视频可以通过更广泛的范围和更广泛的亮度范围更现实地重现现实场景。 HDR视频资源仍然很少，大多数视频仍以SDR（标准动态范围）格式存储。因此，SDRTV-TO-HDRTV转换（SDR视频到HDR视频）可以显着增强用户的视频观看体验。由于相邻视频帧之间的相关性很高，因此利用多个帧信息的方法可以提高转换后的HDRTV的质量。因此，我们为SDRTV提出了一个多帧融合神经网络\ textbf {dslnet}，以进行HDRTV转换。我们首先提出了一个动态的时空特征对齐模块\ textbf {dmfa}，该模块可以对齐和融合多框架。然后，新型时空特征调制模块\ textbf {stfm}，STFM提取相邻帧的时空信息，以进行更准确的特征调制。最后，我们设计了具有大核的质量增强模块\ textbf {lkqe}，可以增强生成的HDR视频的质量。为了评估所提出方法的性能，我们使用HDR10标准的HDR视频构建了相应的多帧数据集，以对不同方法进行全面评估。实验结果表明，我们的方法获得了最先进的性能。数据集和代码将发布。
HDR(High Dynamic Range) video can reproduce realistic scenes more realistically, with a wider gamut and broader brightness range. HDR video resources are still scarce, and most videos are still stored in SDR (Standard Dynamic Range) format. Therefore, SDRTV-to-HDRTV Conversion (SDR video to HDR video) can significantly enhance the user's video viewing experience. Since the correlation between adjacent video frames is very high, the method utilizing the information of multiple frames can improve the quality of the converted HDRTV. Therefore, we propose a multi-frame fusion neural network \textbf{DSLNet} for SDRTV to HDRTV conversion. We first propose a dynamic spatial-temporal feature alignment module \textbf{DMFA}, which can align and fuse multi-frame. Then a novel spatial-temporal feature modulation module \textbf{STFM}, STFM extracts spatial-temporal information of adjacent frames for more accurate feature modulation. Finally, we design a quality enhancement module \textbf{LKQE} with large kernels, which can enhance the quality of generated HDR videos. To evaluate the performance of the proposed method, we construct a corresponding multi-frame dataset using HDR video of the HDR10 standard to conduct a comprehensive evaluation of different methods. The experimental results show that our method obtains state-of-the-art performance. The dataset and code will be released.
