Pan-sharpening is a fundamental task of remote sensing, aiming to produce a synthetic image having high spatial and spectral resolution of original panchromatic and multispectral images. In recent years, as in other tasks of the remote sensing field, deep learning based approaches have been developed for this task. In this research, a detailed comparative analysis was conducted to evaluate the performance and visual quality of pan-sharpening results from traditional algorithms and deep learning-based models. For this purpose, the deep learning based methods that are CNN based pan-sharpening (PNN), Multiscale and multi-depth convolutional neural networks (MSDCNN) and Pan-sharpened Generative Adversarial Networks (PSGAN) and traditional methods that are Brovey, PCA, HIS, Indusion and PRACS were applied. Analysis was performed on regions with different land cover characteristics to evaluate the stability of the methods. In addition, effects of the filter size, spectral indices, activation and loss functions on the pan-sharpening were investigated. For the accuracy assessment, commonly used with-reference and without- reference quality metrics were computed in addition to visual quality evaluations. According to results, the deep learning-based methods provided promising results in both the reduced resolution and full resolution experiments, while PRACS method outperformed other traditional algorithms in most of the experimental configurations.