De-rendering Stylized Texts

被引:1
|
作者
Shimoda, Wataru [1 ]
Haraguchi, Daichi [2 ]
Uchida, Seiichi [2 ]
Yamaguchi, Kota [1 ]
机构
[1] CyberAgent, Tokyo, Japan
[2] Kyushu Univ, Fukuoka, Japan
关键词
D O I
10.1109/ICCV48922.2021.00111
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Editing raster text is a promising but challenging task. We propose to apply text vectorization for the task of raster text editing in display media, such as posters, web pages, or advertisements. In our approach, instead of applying image transformation or generation in the raster domain, we learn a text vectorization model to parse all the rendering parameters including text, location, size, font, style, effects, and hidden background, then utilize those parameters for reconstruction and any editing task. Our text vectorization takes advantage of differentiable text rendering to accurately reproduce the input raster text in a resolution-free parametric format. We show in the experiments that our approach can successfully parse text, styling, and background information in the unified model, and produces artifact-free text editing compared to a raster baseline.
引用
收藏
页码:1056 / 1065
页数:10
相关论文
共 50 条
  • [1] Neural Scene De-rendering
    Wu, Jiajun
    Tenenbaum, Joshua B.
    Kohli, Pushmeet
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 7035 - 7043
  • [2] De-rendering the World's Revolutionary Artefacts
    Wu, Shangzhe
    Makadia, Ameesh
    Wu, Jiajun
    Snavely, Noah
    Tucker, Richard
    Kanazawa, Angjoo
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 6334 - 6343
  • [3] De-rendering 3D Objects in the Wild
    Wimbauer, Felix
    Wu, Shangzhe
    Rupprecht, Christian
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 18469 - 18478
  • [4] From Pixels to Physics: Probabilistic Color De-rendering
    Xiong, Ying
    Saenko, Kate
    Darrell, Trevor
    Zickler, Todd
    [J]. 2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 358 - 365
  • [5] COLOR DE-RENDERING USING COUPLED DICTIONARY LEARNING
    Rushdi, Muhammad
    Ali, Mohsen
    Ho, Jeffrey
    [J]. 2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, : 315 - 319
  • [6] Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata
    Nam, Seonghyeon
    Punnappurath, Abhijith
    Brubaker, Marcus A.
    Brown, Michael S.
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 17683 - 17692
  • [7] Stylized rendering for anatomic visualization
    Lee, Tong-Yee
    Yan, Chung-Ren
    Chi, Ming-Te
    [J]. COMPUTING IN SCIENCE & ENGINEERING, 2007, 9 (01) : 13 - 19
  • [8] Manga Stylized Rendering in VR
    Guertault, Julien
    Setbon, Elie
    Martishevsky, Pavel
    [J]. SA'18: SIGGRAPH ASIA 2018 COURSES, 2018,
  • [9] Stable stylized wireframe rendering
    Tang, Chen
    Li, Sheng
    Wang, Guoping
    Zang, Yutong
    [J]. COMPUTER ANIMATION AND VIRTUAL WORLDS, 2010, 21 (3-4) : 411 - 421
  • [10] Stylized Rendering as a Function of Expectation
    West, Rex
    Mukherjee, Sayan
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2024, 43 (04):