Most consumer-grade digital cameras can only capture a limited range of luminance in real-world scenes due to sensor constraints. Besides, noise and quantization errors are often introduced in the imaging process. In order to obtain high dynamic range (HDR) images with excellent visual quality, the most common solution is to combine multiple images with different exposures. However, it is not always feasible to obtain multiple images of the same scene and most HDR reconstruction methods ignore the noise and quantization loss. In this work, we propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization. The network consists of a UNet-style base network to make full use of the hierarchical multi-scale information, a condition network to perform pattern-specific modulation and a weighting network for selectively retaining information. Moreover, we propose a Tanh_L1 loss function to balance the impact of over-exposed values and well-exposed values on the network learning. Our method achieves the state-of-the-art performance in quantitative comparisons and visual quality. The proposed HDRUNet model won the second place in the single frame track of NITRE2021 High Dynamic Range Challenge.
翻译:由于传感器的限制,大多数消费者级数字相机只能捕捉现实世界场景中有限的亮度。此外,在成像过程中往往会引入噪音和量化错误。为了获得高动态范围(HDR)图像,最常用的解决方案是将多种图像与不同曝光量相结合。然而,获取同一场景的多种图像并不总可行,大多数《人类发展报告》的重建方法忽视了噪音和量化损失。在这项工作中,我们提议采用一种新的基于学习的方法,使用空间动态编码解码网络(HDHRUNet)来学习对单一图像的《人类发展报告》重建进行端到端映图,并进行分辨和分解。这个网络由UNet式的基础网络组成,以充分利用等级化多尺度信息,即进行特定模式调制的条件网络和有选择地保留信息的加权网络。此外,我们提议采用坦赫-L1损失功能,以平衡过度曝光的值和对网络应用的数值的影响。我们的方法在SDHRDSDS-21的第二个图像质量和数字模型中实现了州-Rireal-reaforal 格式上的拟议国家Siral-real-real-real sal-viewal-forgal sal-formal-formal-formal sal-formal-formal-formal-formal-formal-fal-formal-formal-fal-formal-formal-formal-formal sal-formal-formal-fal-formal-fal-fal-fal-fal-fal-fal-fal-formal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-fal-formal-fal-formal-fal-fal-fal-fal-fal-fal