幸运高动态范围智能手机成像
Lucky High Dynamic Range Smartphone Imaging
AI总结：
本文提出一种基于轻量级网络的智能手机成像方法，通过线性RAW像素间接捕捉高动态范围，避免幻觉伪影，验证了其在合成和真实图像上的泛化能力。
摘要：
尽管人类眼睛可以感知约20档的动态范围，但智能手机相机传感器仍受限于约12档，尽管经过数十年的研究。已经提出了多种高动态范围（HDR）图像捕获和处理技术，在实践中，它们可以将动态范围扩展3-5档用于手持摄影。本文提出了一种利用手持智能手机相机和适用于移动设备的轻量级网络来稳健捕获动态范围的方法。我们的方法间接地在括号曝光的线性RAW像素上操作。最终HDR图像中的每个像素都是输入邻域像素的凸组合，经过曝光调整，因此避免了近期深度图像合成网络中常见的幻觉伪影。我们验证了我们的系统在合成图像和未见过的真实括号图像上的性能——我们确认了该方法在智能手机相机捕获上的零样本泛化能力。我们的迭代推理架构能够处理任意数量的括号输入照片，我们展示了包含3-9张图像的捕获堆栈的例子。我们的训练过程仅依赖于合成捕获，却能泛化到多个相机的未见过的真实照片。此外，我们还展示了这种训练方案能提升其他SOTA方法在其预训练后的表现。
英文摘要：
While the human eye can perceive an impressive twenty stops of dynamic range, smartphone camera sensors remain limited to about twelve stops despite decades of research. A variety of high dynamic range (HDR) image capture and processing techniques have been proposed, and, in practice, they can extend the dynamic range by 3-5 stops for handheld photography. This paper proposes an approach that robustly captures dynamic range using a handheld smartphone camera and lightweight networks suitable for running on mobile devices. Our method operates indirectly on linear raw pixels in bracketed exposures. Every pixel in the final HDR image is a convex combination of input pixels in the neighborhood, adjusted for exposure, and thus avoids hallucination artifacts typical of recent deep image synthesis networks. We validate our system on both synthetic imagery and unseen real bracketed images -- we confirm zero-shot generalization of the method to smartphone camera captures. Our iterative inference architecture is capable of processing an arbitrary number of bracketed input photos, and we show examples from capture stacks containing 3--9 images. Our training process relies only on synthetic captures yet generalizes to unseen real photos from several cameras. Moreover, we show that this training scheme improves other SOTA methods over their pretrained counterparts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
