Boosting The Performance of Weakly-Supervised 3D Human Pose Estimators With Pose Prior Regularizers

Prior to training convolutional neural networks (CNNs) for im- age quality assessment (IQA), input normalization is sometimes rec- ommended and sometimes not, according to the literature. Although input normalization is known to improve model training and helps in learning important features, it may result in the loss of informa- tion such as contrast, color, and luminance. To better explore this issue, we conduct an empirical study to first investigate the effect of normalization on model performance and then which normalization method best fits IQA among existing methods. The performances of the selected methods are statistically compared with three basic scal- ing methods. The application of normalization is found to be statisti- cally significant on three IQA databases. The performance improve- ment on the overall databases, as well as per-individual degradation, is demonstrated in the experimental results.