布局

SOTA Layout generation

  1. @inbook{10.1145/3474085.3475497,
  2. author = {Kikuchi, Kotaro and Simo-Serra, Edgar and Otani, Mayu and Yamaguchi, Kota},
  3. title = {Constrained Graphic Layout Generation via Latent Optimization},
  4. year = {2021},
  5. isbn = {9781450386517},
  6. publisher = {Association for Computing Machinery},
  7. address = {New York, NY, USA},
  8. url = {https://doi.org/10.1145/3474085.3475497},
  9. abstract = {It is common in graphic design humans visually arrange various elements according
  10. to their design intent and semantics. For example, a title text almost always appears
  11. on top of other elements in a document. In this work, we generate graphic layouts
  12. that can flexibly incorporate such design semantics, either specified implicitly or
  13. explicitly by a user. We optimize using the latent space of an off-the-shelf layout
  14. generation model, allowing our approach to be complementary to and used with existing
  15. layout generation models. Our approach builds on a generative layout model based on
  16. a Transformer architecture, and formulates the layout generation as a constrained
  17. optimization problem where design constraints are used for element alignment, overlap
  18. avoidance, or any other user-specified relationship. We show in the experiments that
  19. our approach is capable of generating realistic layouts in both constrained and unconstrained
  20. generation tasks with a single model. The code is available at https://github.com/ktrk115/const_layout.},
  21. booktitle = {Proceedings of the 29th ACM International Conference on Multimedia},
  22. pages = {88–96},
  23. numpages = {9}
  24. }

LayoutGAN++

可视化图表合成

可视化图表类型种类相当丰富,而且在不断增加. 自动化的各种类型图表生成成为可视化领域研究热点
可以参考图表生成/推荐的综述

比如可视推荐追求自动从输入的数据中构建 常见的折线图 饼图等 rank完推荐给用户,也可以视为一种生成任务

密度图
http://chenhui.li/
可视化图表传送门 - 图1
GenerativeMap: Visualization and Exploration of Dynamic Density Maps via Generative Learning Model
Chen Chen, Changbo Wang, Xue Bai, Peiying Zhang, Chenhui Li*
IEEE Transactions on Visualization and Computer Graphics, 2020 (Proc. IEEE VIS 2019) (CCF A, JCR Q1)
PDF

流场数据
image.png