Research map / Image generation / Text-to-image diffusion
UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis
Yuanrui Wang, Cong Han, Yafei Li, Zhipeng Jin, Xiawei Li, SiNan Du, Wen Tao, Shuanglong Li, Yi Yang, Chun Yuan, Liu Lin
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 |
|---|---|---|---|
| add adaptive glyph condition (ablation) | UniGlyph · MiniText-benchmark | Sen.Acc: 0.7724 -> 0.7849 | Improved |
| add adaptive glyph condition (ablation) | UniGlyph · MiniText-benchmark | NED: 0.9348 -> 0.9507 | Improved |
| add adaptive glyph condition (ablation) | UniGlyph · MiniText-benchmark | ClipScore: 0.8064 -> 0.8097 | Improved |
| add Gaussian blur to adaptive blending (ablation) | UniGlyph · MiniText-benchmark | ClipScore: 0.7963 -> 0.8097 | Improved |
| add Gaussian blur to adaptive blending (ablation) | UniGlyph · MiniText-benchmark | Sen.Acc: 0.7851 -> 0.7849 | No clear effect |
| add glyph region loss (lambda=1) (ablation) | UniGlyph · Anyword 512x512 | Sen.Acc: 0.8179 -> 0.8188 | Improved |
| add glyph region loss (lambda=1) (ablation) | UniGlyph · Anyword 512x512 | NED: 0.8952 -> 0.8958 | Improved |
| add glyph region loss (lambda=1) (ablation) | UniGlyph · Anyword 512x512 | ClipScore: 0.7868 -> 0.7896 | Improved |
| increase lambda from 1 to 4 (ablation) | UniGlyph · Anyword 512x512 | Sen.Acc: 0.8188 -> 0.8158 | Hurt |
| use lambda 0.01 instead of 0 (ablation) | UniGlyph · Anyword 512x512 | Sen.Acc: 0.8179 -> 0.8161 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GlyphDraw2 — GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025) · better on 4 of 4 shared results
- AnyText-V1.1 — AnyText: Multilingual Visual Text Generation and Editing (ICLR 2024) · better on 4 of 4 shared results
- ControlNet — ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback (ECCV 2024) · better on 4 of 4 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
- GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing (CVPR 2025 · similarity 0.91)
- GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors (NeurIPS 2026 · similarity 0.90)
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025 · similarity 0.90)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024 · similarity 0.89)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.89)
- AnyText: Multilingual Visual Text Generation and Editing (ICLR 2024 · similarity 0.88)
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.
