论文标题
单位图HDR重建通过学习逆转摄像机管道
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
论文作者
论文摘要
从单个低动态范围（LDR）输入图像中恢复高动态范围（HDR）图像，这是有挑战性的，这是由于量化和摄像机传感器的量化不足/过度暴露区域中缺少细节。与现有基于学习的方法相反，我们的核心思想是将LDR图像形成管道的域知识纳入我们的模型。我们将HDRTO-LDR图像形成管道建模为（1）动态范围剪辑，（2）来自相机响应函数的非线性映射，以及（3）量化。然后，我们建议学习三个专门的CNN来扭转这些步骤。通过将问题分解为特定的子任务，我们实施了有效的物理限制，以促进对单个子网络的培训。最后，我们共同微调整个模型的端到端，以减少误差积累。通过对不同图像数据集进行广泛的定量和定性实验，我们证明了所提出的方法对最先进的单像HDR重建算法的表现有利。
Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.
