AI Paper Atlas

Research map / Image generation / Editing and style transfer

UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

Tianshuo Xu, Kai Wang, ZhiFei Chen, Leyi Wu, Tianshui Wen, Fei Chao, Ying-Cong Chen

ICLR 2026 · Image generation › Editing and style transfer · approach: Texture and sketch synthesis · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
use UniCalli instead of Doubao for generationUniCalli · Calligraphy generation user studyStyle Fidelity: 2.413 -> 4.267Improved
use UniCalli instead of FontDiffuser for generationUniCalli · Calligraphy generation user studyGlyph Accuracy: 4.950 -> 4.827No clear effect
use UniCalli instead of Doubao for generationUniCalli · Calligraphy generation user studyOverall Preference: 3.933 -> 4.560Improved
use UniCalli instead of CalliReader for recognitionUniCalli · Character recognition totalcharacter accuracy: 0.533 -> 0.540Improved
use UniCalli instead of Ernie-4.5 for Cursive/Cao recognitionUniCalli · Character recognition Cursive/Caocharacter accuracy: 0.255 -> 0.109Hurt
use UniCalli instead of CalliReader for Running/Xing recognitionUniCalli · Character recognition Running/Xingcharacter accuracy: 0.658 -> 0.528Hurt
use UniCalli instead of OracleNet for oracle bone recognitionUniCalli · Oracle bone script recognitionrecognition accuracy (%): 73.9 -> 62.5Hurt
use UniCalli instead of GOT-OCR2.0 on out-of-domain CalliBenchUniCalli · CalliBench EasyF1: 0.593 -> 0.498Hurt
use UniCalli instead of GPT-4o on CalliBenchUniCalli · CalliBench EasyF1: 0.400 -> 0.498Improved
set conditional dropout rate to 0.05 rather than higher or lower (ablation)UniCalli · calligraphy generationstyle and glyph qualityImproved
add Duplicate RoPE with Modulated Embedding, joint training and conditional dropout to FLUX baseline (ablation)UniCalli · calligraphy generationL1, SSIM, LPIPS, FIDImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy