We report results from a preliminary study exploring the memorability of spatial scientific visualizations, the goal of which is to understand the visual features that contribute to memorability. The evaluation metrics include three objective measures (entropy, feature congestion, the number of edges), four subjective ratings (clutter, the number of distinct colors, familiarity, and realism), and two sentiment ratings (interestingness and happiness). We curate 1142 scientific visualization (SciVis) images from the original 2231 images in published IEEE SciVis papers from 2008 to 2017 and compute memorability scores of 228 SciVis images from data collected on Amazon Mechanical Turk (MTurk). Results showed that the memorability of SciVis images is mostly correlated with clutter and the number of distinct colors. We further investigate the differences between scientific visualization and infographics as a means to understand memorability differences by data attributes.
Recently, deep-learning-based image super-resolution methods have made remarkable progress. However, most of these methods do not fully exploit the structural feature of the input image, as well as the intermediate features from the intermediate layers, which hinders the ability of detail recovery. To deal with this issue, we propose a gradient-guided and multi-scale feature network for image super-resolution (GFSR). Specifically, a dual-branch structure network is proposed, including the trunk branch and the gradient one, where the latter is used to extract the gradient feature map as structural prior to guide the image reconstruction process. Then, to absorb features from different layers, two effective multi-scale feature extraction modules, namely residual of residual inception block (RRIB) and residual of residual receptive field block (RRRFB), are proposed and embedded in different network layers. In our RRIB and RRRFB structures, an adaptive weighted residual feature fusion block (RFFB) is investigated to fuse the intermediate features to generate more beneficial representations, and an adaptive channel attention block (ACAB) is introduced to effectively explore the dependencies between channel features to further boost the feature representation capacity. Experimental results on several benchmark datasets demonstrate that our method achieves superior performance against state-of-the-art methods in terms of both subjective visual quality and objective quantitative metrics.
Recently, the deep-learning-based image super-resolution methods have achieved astounding advancement. Whereas most of these methods utilize features from the low-resolution image space exclusively, and ignore the dependency between contextual features simultaneously, resulting in their limited ability to restore details. To this end, a multi-stage enhancement image network for super-resolution (MESR) is proposed. The network consists of two stages, where the first stage is used to generate a coarse reconstructed image, and the second one is to refine the coarse image, which enhances the super-resolution performance. Specifically, in the first stage, to acquire more abundant features, an effective funnel-like multi-scale feature extractor is proposed, incorporating a channel attention mechanism to boost the feature representation capability. Moreover, an adaptive weighted residual feature fusion block is designed to effectively explore and exploit the dependency between contextual features for generating more beneficial features. In the second stage, a refinement block is proposed to additionally strengthen the details of the reconstructed image by exploring the feature information from the high-resolution image space. Experimental results demonstrate that the proposed method achieves superior performance against the state-of-the-art SR methods in terms of both subjective visual quality and objective quantitative metrics.