We present a method of generating high dynamic range(HDR)radiance maps from a single low dynamic range(LDR)image and its camera response function(CRF).The method first models and estimates the inverse CRF and then mul...We present a method of generating high dynamic range(HDR)radiance maps from a single low dynamic range(LDR)image and its camera response function(CRF).The method first models and estimates the inverse CRF and then multiplies the inverse CRF by a weighting function to make it smooth near the maximum and minimum pixel values,and finally conducts the smooth inverse CRF on the input LDR image to generate HDR image.In the method,the inverse CRF is estimated using one single LDR image and an empirical model of CRF,based on measured RGB distributions at color edges.Unlike most existing methods,the proposed method expands image from both high and low luminance regions.Thus,the algorithm can avoid the artifacts and detail loss in dark area which results from extending image only from bright region.Extensive experimental results show that the approach induces less contrast distortion and produces high visual quality HDR image.展开更多
基金supported by the National Natural Science Foundation of China (61401072)
文摘We present a method of generating high dynamic range(HDR)radiance maps from a single low dynamic range(LDR)image and its camera response function(CRF).The method first models and estimates the inverse CRF and then multiplies the inverse CRF by a weighting function to make it smooth near the maximum and minimum pixel values,and finally conducts the smooth inverse CRF on the input LDR image to generate HDR image.In the method,the inverse CRF is estimated using one single LDR image and an empirical model of CRF,based on measured RGB distributions at color edges.Unlike most existing methods,the proposed method expands image from both high and low luminance regions.Thus,the algorithm can avoid the artifacts and detail loss in dark area which results from extending image only from bright region.Extensive experimental results show that the approach induces less contrast distortion and produces high visual quality HDR image.
文摘单图像高动态范围(High Dynamic Range,HDR)重建能够避免多曝光HDR成像可能造成的鬼影伪像,正受到广泛研究.然而,现有方法由于缺乏对重要信息的关注,尚不能很好地恢复曝光不良区域的细节信息.为解决该问题,本文提出了一种基于多重注意力和感知加权学习的单图像HDR重建方法,旨在从单幅低动态范围图像中推断出高保真的HDR图像.具体而言,考虑到恢复曝光不良区域需参考其他区域的补偿信息,本文设计了具有全局-局部感受野的多重注意力视觉Transformer(Multi-Attention Vision Transformer,MA-ViT),其将深度可分离卷积和注意力机制相结合,从而实现更有效的全局和局部特征提取与交互.此外,还提出了一种损失感知加权图以引导网络聚焦曝光不良区域,进一步提升HDR重建质量.本文在多个基准数据集上构建了全面的对比实验,结果表明所提出方法相较于目前最先进的方法在平均峰值信噪比(Peak Signal to Noise Ratio,PSNR)上提高了0.23 dB,同时生成了具有更高视觉质量的HDR重建结果.
