GlyphAtlas disentangles stroke detail from layout for accurate scene text synthesis
Luozheng Qin · hf · 2026-11-17
Researchers from Xiamen University and Fudan University present GlyphAtlas for scene text synthesis. A dedicated glyph atlas with atlas-anchored attention disentangles stroke detail from layout, providing fine-grained stroke references during generation.
Qualitative results show stroke-accurate text blending seamlessly into dense, high-density scenes such as movie posters, departure boards, and storefront signage, with improved stroke accuracy and zero-shot transfer.
More from Multimodal
- PKU & Tencent Hunyuan's MovieRoll extends streaming video generation to 60s with 78% KV-cache savings — Yunyang Ge · 2026-11-17
- UMM-JEPA: predicting continuous perceptual representations beats discrete codes for unified multimodal models — Yucheng Zhou · 2026-11-17
- Built with ChatGPT: Forge extension tames 30,000-LoRA collections with incremental loading — Artistic-Account-423 · 2026-11-17
- AI-generated Godzilla-style kaiju video of Tokyo street panic impresses — Careful-Loquat-8117 · 2026-11-17
- AI-generated video shows how parental anger quietly erodes the bond with your child — HeyZoyaKhan · 2026-11-17
- Midjourney prompt share: candid morning-stretch portrait with full v8.2 prompt — tisch_eins · 2026-11-17