End-to-End Image Patch Quality Assessment for Image/Video With Compression Artifacts

Abstract

In this paper, we present an experimental image quality assessment (IQA) method for image/ video patches with compression artifacts. Using the High Efficiency Video Coding (HEVC) standard, we create a new database of image patches with compression artifacts. Then, we conduct a completed subjective testing process to obtain the 'ground truth' quality scores for the mentioned database. Finally, we employ an end-to-end learning method to estimate the IQA model for the patches with HEVC compression artifacts. In such proposed method, a modified convolutional neural network (CNN) architecture is exploited for feature extraction while an adaptive moment estimation optimizer solution is used to perform the training process. Experimental results show that the proposed end-to-end IQA method significantly outperforms the relevant IQA benchmarks, especially when the compression artifacts are strongly realized in image/video patches. The proposed IQA method is expected to drive a new set of image/video compression solutions in future image/video coding and transmissions.

Improving Image Compression With Adjacent Attention and Refinement Block

“…The work in [10] introduced a very similar notion by taking into account two sorts of contexts, bit consuming contexts (that is, hyperprior) and bit-free contexts (that is, auto-regressive model), achieving a context-adaptive entropy model. Although these methods enhance the compression performance, they also greatly raise the compression artifacts [11] due to the quantization process during the entropy coding and have stacked by limited respective fields in latent space.…”