arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.03536eess.IVcs.CV
收藏

学习像素自适应权重的人像照片修图

Learning Pixel-Adaptive Weights for Portrait Photo Retouching

Binglu Wang, Chengzhe Lu, Dawei Yan, Yongqiang Zhao

摘要:

人像照片修图是一项强调人体区域优先和组级一致性的照片修图任务。基于查找表的方法通过学习图像自适应权重来组合三维查找表(3D LUT)并进行像素到像素的颜色变换来实现有希望的修饰性能。然而,该范例忽略了局部上下文提示,并且当肖像像素和背景像素表现出相同的原始RGB值时,将相同的变换应用于肖像像素和背景像素。相比之下,专家通常进行不同的操作来调整肖像区域和背景区域的色温和色调。这启发我们对局部上下文线索进行建模,以显式地提高修饰质量。首先,我们考虑一个图像补丁和预测像素自适应查找表的权重,以精确地修饰中心像素。其次,由于相邻像素对中心像素表现出不同的亲和力,我们估计了一个局部注意掩模来调节相邻像素的影响。第三,可以通过应用监督来进一步提高局部注意力掩模的质量,该监督基于由地面实况肖像掩模计算的亲和图。至于组级一致性,我们建议直接约束Lab空间中的平均颜色分量的方差。在PPR10K数据集上的大量实验验证了该方法的有效性,例如,在高分辨率照片上,PSNR度量获得超过0.5的增益,而组级一致性度量获得至少2.1的降低。

英文摘要:

Portrait photo retouching is a photo retouching task that emphasizes human-region priority and group-level consistency. The lookup table-based method achieves promising retouching performance by learning image-adaptive weights to combine 3-dimensional lookup tables (3D LUTs) and conducting pixel-to-pixel color transformation. However, this paradigm ignores the local context cues and applies the same transformation to portrait pixels and background pixels when they exhibit the same raw RGB values. In contrast, an expert usually conducts different operations to adjust the color temperatures and tones of portrait regions and background regions. This inspires us to model local context cues to improve the retouching quality explicitly. Firstly, we consider an image patch and predict pixel-adaptive lookup table weights to precisely retouch the center pixel. Secondly, as neighboring pixels exhibit different affinities to the center pixel, we estimate a local attention mask to modulate the influence of neighboring pixels. Thirdly, the quality of the local attention mask can be further improved by applying supervision, which is based on the affinity map calculated by the groundtruth portrait mask. As for group-level consistency, we propose to directly constrain the variance of mean color components in the Lab space. Extensive experiments on PPR10K dataset verify the effectiveness of our method, e.g. on high-resolution photos, the PSNR metric receives over 0.5 gains while the group-level consistency metric obtains at least 2.1 decreases.

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。

↑