Research map / Image generation / Text-to-image diffusion
TE141K: Artistic Text Benchmark for Text Effect Transfer
Shuai Yang, Wenjing Wang, Jiaying Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use TET-GAN instead of T-Effect (second best) | TET-GAN · General text effect transfer | PSNR: 21.402 -> 27.626 | Improved |
| use TET-GAN instead of Pix2pix | TET-GAN · General text effect transfer | user score: 3.08 -> 4.62 | Improved |
| use TET-GAN+ instead of T-Effect | TET-GAN+ · Supervised one-reference text effect transfer | PSNR: 18.654 -> 20.192 | Improved |
| use TET-GAN+ instead of T-Effect on style loss | TET-GAN+ · Supervised one-reference text effect transfer | style loss: 0.0022 -> 0.0026 | Hurt |
| apply one-reference strategy to Pix2pix (Pix2pix+) vs TET-GAN+ | TET-GAN+ · Supervised one-reference text effect transfer | PSNR: 16.656 -> 20.192 | Improved |
| use TET-GAN+ instead of UT-Effect | TET-GAN+ · Unsupervised one-reference text effect transfer | PSNR: 14.877 -> 18.724 | Improved |
| use TET-GAN+ instead of UT-Effect | TET-GAN+ · Unsupervised one-reference text effect transfer | user score: 2.12 -> 3.90 | Improved |
| add reconstruction loss and feature loss (ablation) | TET-GAN · TE141K text effect transfer | visual quality | Improved |
| add feature loss (ablation) | TET-GAN · TE141K text effect transfer | visual quality | Improved |
| pretrain on TE141K instead of training from scratch (ablation) | TET-GAN+ · one-reference text effect transfer | visual quality | Improved |
| add adversarial augmentation with unpaired TE141K-E data (ablation) | TET-GAN · semisupervised text effect transfer | visual quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StarGAN — StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- TET-GAN: Text Effects Transfer via Stylization and Destylization (AAAI 2019 · similarity 0.93)
- Alchemist: Turning Public Text-to-Image Data into Generative Gold (NeurIPS 2025 · similarity 0.87)
- OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation (NeurIPS 2025 · similarity 0.86)
- Towards Visual Text Design Transfer Across Languages (NeurIPS 2024 · similarity 0.86)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024 · similarity 0.86)
- Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
