论文标题
学习加权图在合理范围内的位深度扩展
Learning Weighting Map for Bit-Depth Expansion within a Rational Range
论文作者
论文摘要
位深度扩展（BDE）是从低位（LBD）源显示高点（HBD）图像的新兴技术之一。现有的BDE方法没有针对各种BDE情况的统一解决方案，并且直接学习从LBD图像到HBD图像中所需值的每个像素的映射，这可能会改变给定的高阶位并导致与地面真相的巨大偏差。在本文中，我们设计了一些位恢复网络（BRNET）来学习每个像素的重量，这表明补充值在合理范围内的比率，在不修改给定的高阶位信息的情况下调用了准确的解决方案。为了使网络自适应任何位深度降解，我们以优化的角度研究了问题，并在渐进培训策略下训练网络以提高性能。此外，我们采用Wasserstein距离作为视觉质量指标来评估恢复图像和地面真相之间的颜色分布差异。实验结果表明，我们的方法可以以更少的伪影和假轮廓恢复五颜六色的图像，并且优于较高的PSNR/SSIM结果和下Wasserstein距离的最先进方法。源代码将在https://github.com/yuqing-liu-dut/bit-depth-expansion上提供
Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth. In this paper, we design a bit restoration network (BRNet) to learn a weight for each pixel, which indicates the ratio of the replenished value within a rational range, invoking an accurate solution without modifying the given high-order bit information. To make the network adaptive for any bit-depth degradation, we investigate the issue in an optimization perspective and train the network under progressive training strategy for better performance. Moreover, we employ Wasserstein distance as a visual quality indicator to evaluate the difference of color distribution between restored image and the ground truth. Experimental results show our method can restore colorful images with fewer artifacts and false contours, and outperforms state-of-the-art methods with higher PSNR/SSIM results and lower Wasserstein distance. The source code will be made available at https://github.com/yuqing-liu-dut/bit-depth-expansion
