Purpose: The purpose of this paper is to study a feasible visualization of large-size three-dimension (3D) color models which are beyond the maximum print size of newest paper-based 3D printer used 3D cutting-bonding frame (3D-CBF) and evaluate the effects of cutting angle and layout method on printing time of designed models. Design/methodology/approach: Sixteen models, including cuboid model, cylinder model, hole model and sphere model with different shape features, were divided into two symmetric parts and printed by the Mcor IRIS HD 3D printer. Before printing, two sub-parts were rearranged in one of three layout methods. Nine scaled sizes of original models were printed to find the quantitative relationship between printing time and scale values in each type. For the 0.3 times of original models, six cutting angles were evaluated in detail. Findings: The correlation function about colorization time and printed pages was proposed. Based on 3D-CBF, the correlation between printing time and scale size is statistically defined. Optimization parameters of designed parts visualization about cutting angel and layout method were found, even if their statistical results were difficult to model their effects on printing time of specimens. Research limitations/implications: The research is comparative and limited to the special models and used procedures. Originality/value: The paper provides a feasible visualization and printing speed optimization methods for the further industrialization of 3D paper-based printing technology in cultural creative field.
Specular highlight removal ensures the acquisition of high-quality images, which finds its important applications in stereo matching, text recognition and image segmentation. In order to prevent the leakage of images containing personal information, such as identification card (ID) photos, clients often train specular highlight removal models using local data resulting in a lack of precision and generalization of the trained model. To address this challenge, this paper introduces a new method to remove highlight in images using federated learning (FL) and attention generative adversarial network (AttGAN). Specifically, the former builds a global model in the central server and updates the global model by aggregating model parameters of clients. This process does not involve the transmission of image data, which enhances the privacy of clients; the later combining attention mechanisms and generative adversarial network aims to improve the quality of highlight removal by focusing on key image regions, resulting in more realistic and visually pleasing results. The proposed FL-AttGAN method is numerically evaluated, using SD1, SD2 amd RD datasets. The results show that the proposed FL-AttGAN outperforms existent methods.