Abstract: Images are widely used by companies to advertise their products and promote awareness of their brands. The automatic synthesis of advertising images is challenging because the advertising message must be clearly conveyed while complying with the style required for the product, brand, or target audience. In this study, we proposed a data-driven method to capture individual design attributes and the relationships between elements in advertising images with the aim of automatically synthesizing the input of elements into an advertising image according to a specified style. To achieve this multi-format advertisement design, we created a dataset containing 13 280 advertising images with rich annotations that encompassed the outlines and colors of the elements, in addition to the classes and goals of the advertisements. Using our probabilistic models, users guided the style of synthesized advertisements via additional constraints (e.g., context-based keywords). We applied our method to a variety of design tasks, and the results were evaluated in several perceptual studies, which showed that our method improved users’ satisfaction by 7.1% compared to designs generated by nonprofessional students, and that more users preferred the coloring results of our designs to those generated by the color harmony model and Colormind.

针对特定风格的平面广告图像自动生成

[1]Antonacopoulos A, Bridson D, Papadopoulos C, et al., 2009. A realistic dataset for performance evaluation of document layout analysis. 10^th Int Conf on Document Analysis and Recognition, p.296-300.

[2]Borji A, Cheng MM, Jiang H, et al., 2015. Salient object detection: a benchmark. IEEE Trans Image Process, 24(12):5706-5722.

[3]Buldas A, Kroonmaa A, Laanoja R, 2013. Keyless signatures’ infrastructure: how to build global distributed hash-trees. Nordic Conf on Secure IT Systems, p.313-320.

[4]Cao Y, Chan AB, Lau RW, 2012. Automatic stylistic manga layout. ACM Trans Graph, 31(6):141-151.

[5]Charpiat G, Hofmann M, Schölkopf B, 2008. Automatic image colorization via multimodal predictions. European Conf on Computer Vision, p.126-139.

[6]Choi J, Kim C, 2016. Object-aware image thumbnailing using image classification and enhanced detection of ROI. Multim Tools Appl, 75(23):16191-16207.

[7]Geigel J, Loui A, 2003. Using genetic algorithms for album page layouts. IEEE Multim, 10(4):16-27.

[8]Gu Z, Lou J, 2016. Data driven webpage color design. Comput Aid Des, 77:46-59.

[9]Hussain Z, Zhang M, Zhang X, et al., 2017. Automatic understanding of image and video advertisements. IEEE Conf on Computer Vision and Pattern Recognition, p.1705-1715.

[10]Jahanian A, Liu J, Tretter DR, et al., 2012. Automatic design of magazine covers. IS&T/SPIE Electronic Imaging, Article 83020N.

[11]Jiang B, Zhang L, Lu H, et al., 2013. Saliency detection via absorbing Markov chain. IEEE Int Conf on Computer Vision, p.1665-1672.

[12]Labrecque LI, Milne GR, 2012. Exciting red and competent blue: the importance of color in marketing. J Acad Mark Sci, 40(5):711-727.

[13]Li J, Xu T, Zhang J, et al., 2019. LayoutGAN: generating graphic layouts with wireframe discriminator. https://arxiv.org/abs/1901.06767

[14]Li X, Zhao H, Nie G, et al., 2015. Image recoloring using geodesic distance based color harmonization. Comput Vis Media, 1(2):143-155.

[15]Li Y, Qi H, Dai J, et al., 2017. Fully convolutional instance-aware semantic segmentation. IEEE Conf on Computer Vision and Pattern Recognition, p.2359-2367.

[16]Lin S, Hanrahan P, 2013. Modeling how people extract color themes from images. SIGCHI Conf on Human Factors in Computing Systems, p.3101-3110.

[17]Lin S, Ritchie D, Fisher M, et al., 2013. Probabilistic color-by-numbers: suggesting pattern colorizations using factor graphs. ACM Trans Graph, 32(4):37.

[18]Liu KL, Li W, Yang CY, et al., 2019. Intelligent design of multimedia content in Alibaba. Front Inform Technol Electron Eng, 20(12):1657-1664.

[19]O’Donovan P, Agarwala A, Hertzmann A, 2011. Color compatibility from large datasets. ACM Trans Graph, 30(4):63-75.

[20]O’Donovan P, Agarwala A, Hertzmann A, 2014. Learning layouts for single-pagegraphic designs. IEEE Trans Vis Comput Graph, 20(8):1200-1213.

[21]O’Donovan P, Agarwala A, Hertzmann A, 2015. DesignScape: design with interactive layout suggestions. 33^rd Annual ACM Conf on Human Factors in Computing Systems, p.1221-1224.

[22]Qiang YT, Fu YW, Yu X, et al., 2019. Learning to generate posters of scientific papers by probabilistic graphical models. J Comput Sci Techn, 34(1):155-169.

[23]Russell BC, Torralba A, Murphy KP, et al., 2008. Labelme: a database and web-based tool for image annotation. Int J Comput Vis, 77(1-3):157-173.

[24]Scott DW, Sain SR, 2005. 9 – multidimensional density estimation. Handbook Stat, 24:229-261.

[25]Seo S, Park Y, Ostromoukhov V, 2013. Image recoloring using linear template mapping. Multim Tools Appl, 64(2):293-308.

[26]Tang YC, Huang JJ, Yao MT, et al., 2019. A review of design intelligence: progress, problems, and challenges. Front Inform Technol Electron Eng, 20(12):1595-1617.

[27]Tokumaru M, Muranaka N, Imanishi S, 2002. Color design support system considering color harmony. IEEE World Congress on Computational Intelligence, p.378-383.

[28]Tuch AN, Bargas-Avila JA, Opwis K, 2010. Symmetry and aesthetics in website design: it’s a man’s business. Comput Human Behav, 26(6):1831-1837.

[29]Wang TC, Liu MY, Zhu JY, et al., 2018. High-resolution image synthesis and semantic manipulation with conditional GANs. IEEE Conf on Computer Vision and Pattern Recognition, p.8798-8807.

[30]Xu T, Zhang P, Huang Q, et al., 2018. AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. IEEE Conf on Computer Vision and Pattern Recognition, p.1316-1324.

[31]Yang X, Mei T, Xu YQ, et al., 2016. Automatic generation of visual-textual presentation layout. ACM Trans Multim Comput Commun Appl, 12(2):33-55.

[32]You WT, Sun LY, Yang ZY, et al., 2019. Automatic advertising image color design incorporating a visual color analyzer. J Comput Lang, 55:100910.

[33]Yu LF, Yeung SK, Tang CK, et al., 2011. Make it home: automatic optimization of furniture arrangement. ACM Trans Graph, 30(4):86:1-86:12.

[34]Zhang Y, Hu K, Ren P, et al., 2017. Layout style modeling for automating banner design. Thematic Workshops of ACM Multimedia, p.451-459.

[35]Zheng X, Qiao X, Cao Y, et al., 2019. Content-aware generative modeling of graphic design layouts. ACM Trans Graph, 38(4):133.

[36]Zhu JY, Park T, Isola P, et al., 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE Int Conf on Computer Vision, p.2223-2232.