Nowadays, deep-learning image coding solutions have shown similar or better compression efficiency than conventional solutions based on hand-crafted transforms and spatial prediction techniques. These deep-learning codecs require a large training set of images and a training methodology to obtain a suitable model (set of parameters) for efficient compression. The training is performed with an optimization algorithm which provides a way to minimize the loss function. Therefore, the loss function plays a key role in the overall performance and includes a differentiable quality metric that attempts to mimic human perception. The main objective of this paper is to study the perceptual impact of several image quality metrics that can be used in the loss function of the training process, through a crowdsourcing subjective image quality assessment study. From this study, it is possible to conclude that the choice of the quality metric is critical for the perceptual performance of the deep-learning codec and that can vary depending on the image content.

Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model through iterative training on large amounts of data. The optimization process typically involves minimizing the distortion between the decoded and the original ground truth images. This paper focuses on perceptual optimization of learning-based image compression solutions and proposes: i) novel loss function to be used during training and ii) novel subjective test methodology that aims to evaluate the decoded image fidelity. According to experimental results from the subjective test taken with the new methodology, the optimization procedure can enhance image quality for low-rates while offering no advantage for high-rates.