Papers › Handwritten Text Generation from Visual Archetypes

Handwritten Text Generation from Visual Archetypes

27 Mar 2023CVPR 2023 1arXiv:2303.15269archive 2025-07-28

Vittorio Pippi, Silvia Cascianelli, Rita Cucchiara

Generating synthetic images of handwritten text in a writer-specific style is a challenging task, especially in the case of unseen styles and new words, and even more when these latter contain characters that are rarely encountered during training. While emulating a writer's style has been recently addressed by generative models, the generalization towards rare characters has been disregarded. In this work, we devise a Transformer-based model for Few-Shot styled handwritten text generation and focus on obtaining a robust and informative representation of both the text and the style. In particular, we propose a novel representation of the textual content as a sequence of dense vectors obtained from images of symbols written as standard GNU Unifont glyphs, which can be considered their visual archetypes. This strategy is more suitable for generating characters that, despite having been seen rarely during training, possibly share visual details with the frequently observed ones. As for the style, we obtain a robust representation of unseen writers' calligraphy by exploiting specific pre-training on a large synthetic dataset. Quantitative and qualitative results demonstrate the effectiveness of our proposal in generating words in unseen styles and with rare characters more faithfully than existing approaches relying on independent one-hot encodings of the characters.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 28 code samples harvested from 2 repositories linked to this paper: 21 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 14 ran (11 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

aimagelab/vatr officialmentioned in papermentioned on GitHubpytorchMITSyntology: 20 samples, 14 ran (3 instrument-failed) · 6 unverified report
hnam-1765/writevit mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (5 instrument-failed) · 1 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

28 samples harvested: 21 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
3ran; the contract check could not run
12ran
7unverified

Licence: 5 of the 28 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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”. For 9 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

aimagelab/vatr official repository 20 samples, 14 ran (3 instrument-failed) · 6 unverified
Conv2dBlock in 7 papers models/model.py ran · metamorphic tier: deterministic MIT (permissive) · f0b7cc93962197b3 · report fixture: returned Conv2dBlock · level recorded 2026-09-22
FCNDecoder models/model.py ran · metamorphic tier: deterministic MIT (permissive) · 0ce0d022419871d3 · report fixture: returned FCNDecoder · level recorded 2026-09-22
FIDInceptionA models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2648187d673104a6 · report fixture: returned FIDInceptionA · level recorded 2026-09-22
FIDInceptionC models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 643d4a526326f581 · report fixture: returned FIDInceptionC · level recorded 2026-09-22
FIDInceptionE_1 models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · db29adb344f73366 · report fixture: returned FIDInceptionE_1 · level recorded 2026-09-22
FIDInceptionE_2 models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · cd5dedb4fdac4f23 · report fixture: returned FIDInceptionE_2 · level recorded 2026-09-22
PositionalEncoding1D in 5 papers models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9e410fe607bac90c · report fixture: returned PositionalEncoding1D · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/model.py ran · metamorphic tier: deterministic MIT (permissive) · 22c73a1beb759d7d · report fixture: returned ResBlock · level recorded 2026-09-22
ResBlocks in 5 papers models/model.py ran · metamorphic tier: deterministic MIT (permissive) · 4dbb6df05fa94399 · report fixture: returned ResBlocks · level recorded 2026-09-22
UnifontModule models/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 367b22529423f3f6 · report fixture: returned UnifontModule · level recorded 2026-09-22
get_emb in 20 papers models/model.py ran · honoured contract fingerprinted MIT (permissive) · 33805df68cb6892e · report fixture: signature sin_inp:Tensor/2/float · returned Tensor · level recorded 2026-09-22
loss_hinge_dis in 14 papers models/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · d5932c9e19a8f551 · report fixture: signature dis_fake:Tensor/4/float, dis_real:Tensor/4/float, len_text_fake:list/1/int, len_text:list/1/int, mask_loss:bool/0/bool · returned tuple · level recorded 2026-09-22
loss_hinge_gen models/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 20ede13d7691fddd · report fixture: signature dis_fake:Tensor/4/float, len_text_fake:list/1/int, mask_loss:bool/0/bool · returned Tensor · level recorded 2026-09-22
make_one_hot in 15 papers models/model.py ran · our draft was wrong MIT (permissive) · 39075c27b258d2c3 · report fixture: signature labels:Tensor/2/int, len_labels:ndarray/1/int, n_classes:int/0/int · returned Tensor · level recorded 2026-09-22
AdaptiveInstanceNorm2d models/model.py unverified MIT (permissive) · 5db4f1182b19d9c5 · report
Generator in 95 papers models/model.py unverified MIT (permissive) · 1ff1bc3eaf943f05 · report
InceptionV3 models/model.py unverified MIT (permissive) · e66d36581525af67 · report
VATr models/model.py unverified MIT (permissive) · 818355b6821b8174 · report
fid_inception_v3 models/model.py unverified MIT (permissive) · 99c0f27938d0a636 · report
toggle_grad models/model.py unverified MIT (permissive) · c31ec2e6a64fbcac · report
hnam-1765/writevit community (archive-listed) 8 samples, 7 ran (5 instrument-failed) · 1 unverified
D_arch in 21 papers models/BigGAN_networks.py ran MIT (permissive) · d5e0c4c475f7d0ea · report fixture: signature ch:int/0/int, attention:str/0/str, input_nc:int/0/int, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded 2026-09-24
G_arch in 22 papers models/BigGAN_networks.py ran MIT (permissive) · eeee154bc306d46b · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded 2026-09-24
calculate_frechet_distance in 119 papers models/inception.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · 4cee7c1861294d59 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-22
conv3x3 in 1,376 papers models/backbone.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 583f9780bdd00a45 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
get_scheduler in 122 papers models/networks.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 62a8cdfdb51ec275 · report fixture: signature optimizer:Adam/0/?, opt:Options/0/? · returned LambdaLR · level recorded 2026-09-22
gram_schmidt in 32 papers models/BigGAN_layers.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c41836f3e51fa8f1 · report fixture: signature x:Tensor/2/float, ys:list/1/Tensor · returned Tensor · level recorded 2026-09-22
power_iteration in 30 papers models/BigGAN_layers.py ran · our draft was wrong MIT (permissive) · 28d3a35157f2916d · report fixture: signature W:Tensor/2/float, u_:list/1/Tensor, update:bool/0/bool, eps:float/0/float · returned tuple · level recorded 2026-09-25
proj in 38 papers models/BigGAN_layers.py unverified MIT (permissive) here; the stored copy is pointer only · 4015ab1f3ab9b881 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Transformer-based model for Few-Shot styled handwritten text generation (graph method: Transformer-based model for Few-Shot styled handwritten text generation). 20 bricks; individually on a fixture: 14 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. VATr entry · level 0 · unverified · 818355b6821b8174
  2. Generator model · level 0 · unverified · 1ff1bc3eaf943f05
  3. InceptionV3 helper · level 0 · unverified · e66d36581525af67
  4. loss_hinge_dis helper · level 1 · ran; the contract check could not run (RAISES) · d5932c9e19a8f551
  5. loss_hinge_gen helper · level 1 · ran; the contract check could not run (RAISES) · 20ede13d7691fddd
  6. make_one_hot helper · level 1 · ran · our draft was wrong · 39075c27b258d2c3
  7. toggle_grad helper · level 0 · unverified · c31ec2e6a64fbcac
  8. FCNDecoder model · level 1 · ran · 0ce0d022419871d3
  9. PositionalEncoding1D helper · level 1 · ran · 9e410fe607bac90c
  10. UnifontModule helper · level 1 · ran · 367b22529423f3f6
  11. fid_inception_v3 helper · level 0 · unverified · 99c0f27938d0a636
  12. Conv2dBlock helper · level 1 · ran · f0b7cc93962197b3
  13. ResBlocks model · level 1 · ran · 4dbb6df05fa94399
  14. get_emb helper · level 1 · ran · honoured contract · 33805df68cb6892e
  15. FIDInceptionA helper · level 1 · ran · 2648187d673104a6
  16. FIDInceptionC helper · level 1 · ran · 643d4a526326f581
  17. FIDInceptionE_1 helper · level 1 · ran · db29adb344f73366
  18. FIDInceptionE_2 helper · level 1 · ran · cd5dedb4fdac4f23
  19. AdaptiveInstanceNorm2d model · level 0 · unverified · 5db4f1182b19d9c5
  20. ResBlock helper · level 1 · ran · 22c73a1beb759d7d

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.15269") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Text Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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