Editing Text in the Wild
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
In this paper, we are interested in editing text in natural images, which aims to replace or modify a word in the source image with another one while maintaining its realistic look. This task is challenging, as the styles of both background and text need to be preserved so that the edited image is visually indistinguishable from the source image. Specifically, we propose an end-to-end trainable style retention network (SRNet) that consists of three modules: text conversion module, background inpainting module and fusion module. The text conversion module changes the text content of the source image into the target text while keeping the original text style. The background inpainting module erases the original text, and fills the text region with appropriate texture. The fusion module combines the information from the two former modules, and generates the edited text images. To our knowledge, this work is the first attempt to edit text in natural images at the word level. Both visual effects and quantitative results on synthetic and real-world dataset (ICDAR 2013) fully confirm the importance and necessity of modular decomposition. We also conduct extensive experiments to validate the usefulness of our method in various real-world applications such as text image synthesis, augmented reality (AR) translation, information hiding, etc.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283
Conditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025
Cited by
Scene Text Detection and Recognition: The Deep Learning Era
Long, S., He, X., & Yao, C. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01369-0 · Cited by 527
Towards Accurate Scene Text Recognition With Semantic Reasoning Networks
Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., & Ding, E. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01213 · Cited by 385
Self-citationText Recognition in the Wild: A Survey
Chen, X., Jin, L., Zhu, Y., Luo, C., & Wang, T. (2022) · ACM Computing Surveys · doi:10.1145/3440756 · Cited by 205
“e features of backgrounds can be visually similar to the text, which causes additional difficulties in recognition. Instead of complicated feature representations [147] and synthesis approaches [171], [172], an intuitive but rarely noticed solution is to separate the text content from complex backgrounds. Although trad…”
BackgroundToward real text manipulation detection: New dataset and new solution
Luo, D., Liu, Y., Yang, R., Liu, X., Zeng, J., Zhou, Y., & Bai, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2024.110828 · Cited by 25
Self-citationDocument-Image Perceptual Hashing for Content Authentication
Situ, X., Liu, T., Yao, H., Qin, C., & Zhang, X. (2025) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2025.3596854 · Cited by 2
Metadata
- Authors
- Wu, L., Zhang, C., Liu, J., Han, J., Liu, J., Ding, E., & Bai, X.
- Venue
- Proceedings of the 27th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2019-10-15
- Pages
- 1500-1508
- OpenAlex
- W2982148195
- Cited by
- 130
- References
- 4
- FWCI
- 3.88
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.