论文标题
自动图像着色：指标和错误类型
Bias in Automated Image Colorization: Metrics and Error Types
论文作者
论文摘要
当通过基于自动GAN的Deoldify模型上色时，我们测量来自ADE20K数据集的有色图像中存在的色移。我们在原始图像和有色图像之间介绍了细粒度的局部和区域偏置测量，并观察到许多着色效应。我们确认了一般的淡淡效果，还提供了新颖的观察：向训练平均值的转移，普遍的蓝移，图像类别之间的不同色素转移以及三个类别的着色误差的手动分类。
We measure the color shifts present in colorized images from the ADE20K dataset, when colorized by the automatic GAN-based DeOldify model. We introduce fine-grained local and regional bias measurements between the original and the colorized images, and observe many colorization effects. We confirm a general desaturation effect, and also provide novel observations: a shift towards the training average, a pervasive blue shift, different color shifts among image categories, and a manual categorization of colorization errors in three classes.
