Papers › Disentangling Writer and Character Styles for Handwriting Generation

Disentangling Writer and Character Styles for Handwriting Generation

26 Mar 2023CVPR 2023 1arXiv:2303.14736archive 2025-07-28

Gang Dai, Yifan Zhang, Qingfeng Wang, Qing Du, Zhuliang Yu, Zhuoman Liu, Shuangping Huang

Training machines to synthesize diverse handwritings is an intriguing task. Recently, RNN-based methods have been proposed to generate stylized online Chinese characters. However, these methods mainly focus on capturing a person's overall writing style, neglecting subtle style inconsistencies between characters written by the same person. For example, while a person's handwriting typically exhibits general uniformity (e.g., glyph slant and aspect ratios), there are still small style variations in finer details (e.g., stroke length and curvature) of characters. In light of this, we propose to disentangle the style representations at both writer and character levels from individual handwritings to synthesize realistic stylized online handwritten characters. Specifically, we present the style-disentangled Transformer (SDT), which employs two complementary contrastive objectives to extract the style commonalities of reference samples and capture the detailed style patterns of each sample, respectively. Extensive experiments on various language scripts demonstrate the effectiveness of SDT. Notably, our empirical findings reveal that the two learned style representations provide information at different frequency magnitudes, underscoring the importance of separate style extraction. Our source code is public at: https://github.com/dailenson/SDT.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dailenson/sdt officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified report
koninik/htg_evaluation mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran
2unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

dailenson/sdt official repository 10 samples, 8 ran (0 instrument-failed) · 2 unverified
get_mixture_coef models/gmm.py ran MIT (permissive) · 3938029b16a8e652 · report fixture: signature output:Tensor/2/float · returned list · level recorded 2026-09-24
get_pen_loss models/loss.py ran MIT (permissive) · c3c5ed7bdf6dff50 · report fixture: signature z_pi:Tensor/2/float, z_mu1:Tensor/2/float, z_mu2:Tensor/2/float, z_sigma1:Tensor/2/float, z_sigma2:Tensor/2/float, z_corr:Tensor/2/float, z_pen_logits:Tensor/2/float, x1_data:Tensor/2/float, x2_data:Tensor/2/float, pen_data:Tensor/2/float · returned tuple · level recorded 2026-09-24
get_seq_from_gmm models/gmm.py ran MIT (permissive) · 0a53368641da7207 · report fixture: signature gmm_pred:Tensor/1/float · returned Tensor · level recorded 2026-09-24
length_to_mask in 12 papers models/eval_model.py ran MIT (permissive) · 61789a642c162a1b · report fixture: signature length:Tensor/1/int, max_len:NoneType/0/?, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-24
mask_avr_pooling models/eval_model.py ran fingerprinted MIT (permissive) · 977232b5fb66d03c · report fixture: signature x:Tensor/3/float, l:Tensor/1/int · returned Tensor · level recorded 2026-09-24
mask_avr_pooling_rnn models/eval_model.py ran fingerprinted MIT (permissive) · 8acffa1b60bdf3a3 · report fixture: signature x:Tensor/3/float, l:Tensor/1/int · returned Tensor · level recorded 2026-09-24
set_log utils/logger.py ran MIT (permissive) · 9f7efffab3bafdef · report fixture: signature output_dir:str/0/str, cfg_file:str/0/str, log_name:str/0/str · returned dict · level recorded 2026-09-24
tf_2d_normal models/loss.py ran MIT (permissive) · 67b19b6b4b262e2b · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float, mu1:Tensor/2/float, mu2:Tensor/2/float, s1:Tensor/2/float, s2:Tensor/2/float, rho:Tensor/2/float · returned Tensor · level recorded 2026-09-24
assert_and_infer_cfg in 5 papers parse_config.py unverified MIT (permissive) · 87f89dec0143219f · report
build_transformer in 62 papers models/transformer.py unverified MIT (permissive) · d3c210804250a1dc · report
koninik/htg_evaluation community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
affine_transformation utils/auxilary_functions.py ran MIT (permissive) · 22a46289db28df6d · report fixture: signature img:ndarray/2/int, m:float/0/float, s:float/0/float, border_value:NoneType/0/? · returned ndarray · level recorded 2026-09-24
centered utils/auxilary_functions.py ran MIT (permissive) · ae6d12745b44744a · report fixture: signature word_img:ndarray/2/int, tsize:tuple/1/int, centering:tuple/1/float, border_value:NoneType/0/? · returned ndarray · level recorded 2026-09-24
eval_class_epoch htg_style.py ran MIT (permissive) · 271b9e1e885936bf · report fixture: signature model:callable/0/?, validation_data:list/1/tuple, args:Args/0/? · returned tuple · level recorded 2026-09-25
image_resize in 11 papers utils/auxilary_functions.py ran MIT (permissive) · e8bf18bac8135a3c · report fixture: signature img:ndarray/3/float, height:int/0/int, width:NoneType/0/? · returned ndarray · level recorded 2026-09-24
performance htg_style.py ran MIT (permissive) · 67e4aa07555e7628 · report fixture: signature pred:Tensor/2/float, label:Tensor/1/int · returned Tensor · level recorded 2026-09-24
train_class_epoch htg_style.py ran MIT (permissive) · f0595038a8dda9b6 · report fixture: signature model:callable/0/?, training_data:list/1/tuple, optimizer:SGD/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-24

Tasks

Handwriting generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections