Image aesthetics assessment has emerged as a hot topic in recent years due to its potential in numerous high-level vision applications. In this paper, distinguished from existing studies relying on a single label, we propose quantifying image aesthetics by a distribution over multiple quality levels. The distribution-based representation characterizes the disagreement among users' aesthetic preferences regarding the same image, and is also compatible with the traditional task of aesthetic label prediction. Our framework is developed based on fully convolutional networks and enables inputs of varying sizes. In this way, we circumvent the fixed-size constraint of prevalent convolutional neural networks, and avoid the risk of impairing the intrinsic aesthetic appeal of images. Moreover, given the fact that aesthetic perceiving is coupled with semantic understanding, we present a novel semantic-aware hybrid NEtwork (SANE), which harvests the information from object categorization and scene recognition to enhance image aesthetics assessment. Experiments on two benchmark datasets have well verified the effectiveness of our approach in both scenarios of aesthetic distribution prediction and aesthetic label prediction, and highlighted the benefits of input preserving as well as semantic understanding for images.

Pansharpening aims to integrate low-resolution multispectral images (LRMS) and panchromatic images (PAN) to obtain the high-resolution multispectral images (HRMS). As PAN and LRMS images capture the same scene, they have some common information. Due to sensor characteristics differences, they also have unique information. Therefore, recent pansharpening methods separate common and unique features to reduce redundancy. However, they are not explicitly equipped with specific modules to extract common and unique features, which limits redundancy removal. To solve the problems, we propose a pansharpening method using a cross-attention-based module to specifically extract common and unique feature maps from the MS and PAN images. In addition, mutual information maximization and minimization constraints are used to enforce the common and unique features, which can reduce the redundant information. Finally, these features are concatenated to generate the HRMS. Extensive experimental results on QuickBird and Gaofen-2 datasets demonstrate that the proposed method outperforms other methods quantitatively and qualitatively.