Papers › Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling...

Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context

21 Jul 2022arXiv:2207.10273archive 2025-07-28

Chongyu Liu, Lianwen Jin, Yuliang Liu, Canjie Luo, Bangdong Chen, Fengjun Guo, Kai Ding

Text removal has attracted increasingly attention due to its various applications on privacy protection, document restoration, and text editing. It has shown significant progress with deep neural network. However, most of the existing methods often generate inconsistent results for complex background. To address this issue, we propose a Contextual-guided Text Removal Network, termed as CTRNet. CTRNet explores both low-level structure and high-level discriminative context feature as prior knowledge to guide the process of background restoration. We further propose a Local-global Content Modeling (LGCM) block with CNNs and Transformer-Encoder to capture local features and establish the long-term relationship among pixels globally. Finally, we incorporate LGCM with context guidance for feature modeling and decoding. Experiments on benchmark datasets, SCUT-EnsText and SCUT-Syn show that CTRNet significantly outperforms the existing state-of-the-art methods. Furthermore, a qualitative experiment on examination papers also demonstrates the generalization ability of our method. The codes and supplement materials are available at https://github.com/lcy0604/CTRNet.

PaperPDFCodeCode 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 22 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 22 samples from 1 repository, 9 ran (9 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lcy0604/ctrnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 22 samples, 9 ran (0 instrument-failed) · 13 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

22 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 13 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.

9ran
13unverified

Licence: 0 of the 22 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 lcy0604/ctrnet. “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. 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.

lcy0604/ctrnet official repository 22 samples, 9 ran (0 instrument-failed) · 13 unverified
AdversarialLoss models_CTRNet.py ran fingerprinted MIT (permissive) · 06eae0ae5e115c24 · report fixture: signature outputs:Tensor/2/float, is_real:bool/0/bool, is_disc:bool/0/bool · returned Tensor · level recorded 2026-09-22
ConvWithActivation models_CTRNet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 135239d29145820a · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ConvWithActivation_encode models_CTRNet.py ran fingerprinted MIT (permissive) · 94b5cbe5237f7e9d · report fixture: signature input:Tensor/4/float · returned tuple · level recorded 2026-09-22
D_Net models_CTRNet.py ran MIT (permissive) · fa209b1538963765 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
DenseLayer in 9 papers models_CTRNet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 28816304c3e4e4bc · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
LateralConnect models_CTRNet.py ran · metamorphic tier: invariant MIT (permissive) · 7cc637107bac1c93 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
models_CTRNet.py ran fingerprinted MIT (permissive) · b4ca9a91816f9d68 · report fixture: signature tensor_list:Tensor/4/float · returned tuple · level recorded 2026-09-22
RDB models_CTRNet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 0cd90b435a362538 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ResnetBlock in 49 papers models_CTRNet.py ran · metamorphic tier: invariant MIT (permissive) · 6d01e64cec5bf46c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
CTRNet models_CTRNet.py unverified MIT (permissive) · 4635cdc63b1df831 · report
ConvTD_SPADE_refine models_CTRNet.py unverified MIT (permissive) · e503b02c4552fae1 · report
ConvTE_spade models_CTRNet.py unverified MIT (permissive) · c15346bf36f3790c · report
DeConvWithActivation models_CTRNet.py unverified MIT (permissive) · 08bef43cba4a315e · report
Downsample_connect models_CTRNet.py unverified MIT (permissive) · c33bbf8c045f74d5 · report
G_Net models_CTRNet.py unverified MIT (permissive) · 8d65710b92ac9ee8 · report
ResnetBlock_Spade models_CTRNet.py unverified MIT (permissive) · c927665bd23c28e5 · report
SPADE in 10 papers models_CTRNet.py unverified MIT (permissive) · 6c9dabcd0790d01f · report
StructureGen models_CTRNet.py unverified MIT (permissive) · ac4a7e0a62602134 · report
TransformerEncoderLayer in 90 papers models_CTRNet.py unverified MIT (permissive) · 8432e0f043a686c3 · report
VGG16FeatureExtractor models_CTRNet.py unverified MIT (permissive) · 8e1316c982cfa4fe · report
_get_activation_fn in 21 papers models_CTRNet.py unverified MIT (permissive) · b38b74ab50f7c296 · report
create_model in 163 papers models_CTRNet.py unverified MIT (permissive) · a8929ba31c8b7c2b · 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 CTRNet (graph method: CTRNet). 23 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

  1. CTRNet entry · level 0 · unverified · 4635cdc63b1df831
  2. AdversarialLoss loss · level 1 · ran · 06eae0ae5e115c24
  3. D_Net model · level 1 · ran · fa209b1538963765
  4. G_Net model · level 0 · unverified · 8d65710b92ac9ee8
  5. VGG16FeatureExtractor helper · level 0 · unverified · 8e1316c982cfa4fe
  6. create_model helper · level 0 · unverified · a8929ba31c8b7c2b
  7. spectral_norm helper · level 0 · unverified · b189ed0149b76880
  8. ConvTD_SPADE_refine helper · level 0 · unverified · e503b02c4552fae1
  9. StructureGen model · level 0 · unverified · ac4a7e0a62602134
  10. ConvTE_spade helper · level 0 · unverified · c15346bf36f3790c
  11. ConvWithActivation_encode helper · level 1 · ran · 94b5cbe5237f7e9d
  12. DeConvWithActivation helper · level 0 · unverified · 08bef43cba4a315e
  13. LateralConnect helper · level 1 · ran · 7cc637107bac1c93
  14. RDB helper · level 1 · ran · 0cd90b435a362538
  15. ResnetBlock helper · level 1 · ran · 6d01e64cec5bf46c
  16. ConvWithActivation helper · level 1 · ran · 135239d29145820a
  17. Downsample_connect helper · level 0 · unverified · c33bbf8c045f74d5
  18. PositionEmbeddingSine helper · level 1 · ran · b4ca9a91816f9d68
  19. ResnetBlock_Spade helper · level 0 · unverified · c927665bd23c28e5
  20. TransformerEncoderLayer helper · level 0 · unverified · 8432e0f043a686c3
  21. DenseLayer helper · level 1 · ran · 28816304c3e4e4bc
  22. SPADE helper · level 0 · unverified · 6c9dabcd0790d01f
  23. _get_activation_fn helper · level 0 · unverified · b38b74ab50f7c296

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="2207.10273") returns these assemblies with each brick's role and wiring (how to connect).

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