From image quality to patch quality: An Image-Patch Model for No-Reference image quality assessment

Wen Heng, Tingting Jiang

Abstract: Supervised learning is gradually used for image quality assessment (IQA). For the patch-based methods, the `ground truth' quality of patches is essential for training, but in practice it's easy to obtain the ground truth quality of images rather than patches. So we propose an Image-Patch model (IPM) to estimate the `ground truth' quality for patches with known ground truth quality of images. Combined with baseline image quality estimator e.g. convolutional neural network IQA (CNN-IQA), the IPM can reduce the noise in patches' labels and make training more efficiently. The experiments show that the IPM improves the performance of baseline estimator on most of the distortion types while make great progress in evaluating local quality.