论文标题
更多一点：通过比特平板的位深度恢复
A Little Bit More: Bitplane-Wise Bit-Depth Recovery
论文作者
论文摘要
成像传感器在10--12位的动态范围内数字化传入的场景光（即1024---4096音调值）。然后，将传感器图像在相机上处理，最终仅量化为8位（即256个音调值），以符合盛行的编码标准。有许多重要的应用程序，例如高位深度显示器和照片编辑，在其中恢复失去的位深度是有益的。深度神经网络在这项多重重建任务中有效。鉴于量化的低位深度图像作为输入，现有的深度学习方法采用了一种尝试（1）直接估计高位深度图像的单次射击方法，或（2）直接估计高位和低位深度图像之间的残差。相比之下，我们提出了一种训练和推理策略，以逐步恢复剩余的图像bitplane-bitplane。我们的BITPLANE学习框架具有允许在培训期间进行多个监督的优势，并能够使用简单的网络体系结构获得最新的结果。我们在几个图像数据集上广泛测试了我们的方法，并证明了根据量化级别的定量级别，对先前方法的改进从0.5dB到2.3dB。
Imaging sensors digitize incoming scene light at a dynamic range of 10--12 bits (i.e., 1024--4096 tonal values). The sensor image is then processed onboard the camera and finally quantized to only 8 bits (i.e., 256 tonal values) to conform to prevailing encoding standards. There are a number of important applications, such as high-bit-depth displays and photo editing, where it is beneficial to recover the lost bit depth. Deep neural networks are effective at this bit-depth reconstruction task. Given the quantized low-bit-depth image as input, existing deep learning methods employ a single-shot approach that attempts to either (1) directly estimate the high-bit-depth image, or (2) directly estimate the residual between the high- and low-bit-depth images. In contrast, we propose a training and inference strategy that recovers the residual image bitplane-by-bitplane. Our bitplane-wise learning framework has the advantage of allowing for multiple levels of supervision during training and is able to obtain state-of-the-art results using a simple network architecture. We test our proposed method extensively on several image datasets and demonstrate an improvement from 0.5dB to 2.3dB PSNR over prior methods depending on the quantization level.
