Papers › MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting

MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting

12 Mar 2022CVPR 2022 1arXiv:2203.06304archive 2025-07-28

Xiaoguang Li, Qing Guo, Di Lin, Ping Li, Wei Feng, Song Wang

Although achieving significant progress, existing deep generative inpainting methods are far from real-world applications due to the low generalization across different scenes. As a result, the generated images usually contain artifacts or the filled pixels differ greatly from the ground truth. Image-level predictive filtering is a widely used image restoration technique, predicting suitable kernels adaptively according to different input scenes. Inspired by this inherent advantage, we explore the possibility of addressing image inpainting as a filtering task. To this end, we first study the advantages and challenges of image-level predictive filtering for image inpainting: the method can preserve local structures and avoid artifacts but fails to fill large missing areas. Then, we propose semantic filtering by conducting filtering on the deep feature level, which fills the missing semantic information but fails to recover the details. To address the issues while adopting the respective advantages, we propose a novel filtering technique, i.e., Multilevel Interactive Siamese Filtering (MISF), which contains two branches: kernel prediction branch (KPB) and semantic & image filtering branch (SIFB). These two branches are interactively linked: SIFB provides multi-level features for KPB while KPB predicts dynamic kernels for SIFB. As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting. We validate our method on three challenging datasets, i.e., Dunhuang, Places2, and CelebA. Our method outperforms state-of-the-art baselines on four metrics, i.e., L1, PSNR, SSIM, and LPIPS. Please try the released code and model at https://github.com/tsingqguo/misf.

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 22 code samples harvested from 1 repository linked to this paper: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 10 ran (9 with no instrument failure; 1 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.

tsingqguo/misf officialmentioned in papermentioned on GitHubpytorchSyntology: 22 samples, 10 ran (1 instrument-failed) · 12 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: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 12 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
1ran; the contract check could not run
8ran
12unverified

Licence: 22 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 tsingqguo/misf. “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 1 sample 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.

tsingqguo/misf official repository 22 samples, 10 ran (1 instrument-failed) · 12 unverified
AdversarialLoss src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3bc38c44be641e19 · report fixture: returned AdversarialLoss · level recorded 2026-09-22
BaseModel in 92 papers src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · 53fdc1cabe3fdd26 · report fixture: returned BaseModel · level recorded 2026-09-22
Basic src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · e6abeeabd7ed1930 · report fixture: returned Basic · level recorded 2026-09-22
Dataset in 14 papers src/misf.py ran no licence file found · pointer only · 688f3ec6a92f1d08 · report fixture: returned Dataset · level recorded 2026-09-22
Discriminator in 42 papers src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · 463b050a07daa0c8 · report fixture: returned Discriminator · level recorded 2026-09-22
KPN src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · 956f6a72ea5b71ed · report fixture: returned KPN · level recorded 2026-09-22
PSNR in 28 papers
census: 4 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · 699c5755b0231249 · report fixture: returned PSNR · level recorded 2026-09-22
ResnetBlock in 49 papers src/misf.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7e912d934dcaa958 · report fixture: returned ResnetBlock · level recorded 2026-09-22
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 2 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
src/misf.py ran · honoured contract fingerprinted no licence file found · pointer only · caabcc4a49fbf99a · report fixture: signature pred:ndarray/2/float, target:ndarray/2/float · returned float · level recorded 2026-09-22
save_sample_png src/misf.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 3f8793f8bb43aa29 · report fixture: signature sample_folder:str/0/str, sample_name:str/0/str, img_list:list/1/Tensor, name_list:list/1/str, pixel_max_cnt:int/0/int, height:int/0/int, width:int/0/int · returned ndarray · level recorded 2026-09-22
BaseNetwork in 19 papers src/misf.py unverified no licence file found · pointer only · ff4df02a0571a8be · report
InpaintGenerator src/misf.py unverified no licence file found · pointer only · d6f6a2a71da8d427 · report
InpaintingModel src/misf.py unverified no licence file found · pointer only · 75172d9cb8610875 · report
KernelConv src/misf.py unverified no licence file found · pointer only · 60f1c996ef41a253 · report
MISF src/misf.py unverified no licence file found · pointer only · d8a4c87fa38148c3 · report
PerceptualLoss in 5 papers src/misf.py unverified no licence file found · pointer only · 21db58187296e8e8 · report
StyleLoss src/misf.py unverified no licence file found · pointer only · 5dedc9464d136848 · report
VGG19 in 6 papers src/misf.py unverified no licence file found · pointer only · 0122d0f23bd245a5 · report
create_dir in 10 papers src/misf.py unverified no licence file found · pointer only · dc389a4987d62208 · report
create_generator src/misf.py unverified no licence file found · pointer only · 12fe0f3bd5ae7e36 · report
spectral_norm in 42 papers src/misf.py unverified no licence file found · pointer only · b189ed0149b76880 · report
ssim in 112 papers src/misf.py unverified no licence file found · pointer only · 9988abd73490a22f · 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 MISF (graph method: MISF). 22 bricks; individually on a fixture: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. MISF entry · level 0 · unverified · d8a4c87fa38148c3
  2. Dataset helper · level 1 · ran · 688f3ec6a92f1d08
  3. InpaintingModel model · level 0 · unverified · 75172d9cb8610875
  4. PSNR helper · level 1 · ran · 699c5755b0231249
  5. create_dir helper · level 0 · unverified · dc389a4987d62208
  6. psnr helper · level 1 · ran · honoured contract · caabcc4a49fbf99a
  7. save_sample_png helper · level 1 · ran; the contract check could not run (RAISES) · 3f8793f8bb43aa29
  8. ssim helper · level 0 · unverified · 9988abd73490a22f
  9. AdversarialLoss loss · level 1 · ran · 3bc38c44be641e19
  10. BaseModel helper · level 1 · ran · 53fdc1cabe3fdd26
  11. Discriminator model · level 1 · ran · 463b050a07daa0c8
  12. InpaintGenerator model · level 0 · unverified · d6f6a2a71da8d427
  13. PerceptualLoss loss · level 0 · unverified · 21db58187296e8e8
  14. StyleLoss loss · level 0 · unverified · 5dedc9464d136848
  15. BaseNetwork helper · level 0 · unverified · ff4df02a0571a8be
  16. spectral_norm helper · level 0 · unverified · b189ed0149b76880
  17. KernelConv helper · level 0 · unverified · 60f1c996ef41a253
  18. ResnetBlock helper · level 1 · ran · 7e912d934dcaa958
  19. create_generator helper · level 0 · unverified · 12fe0f3bd5ae7e36
  20. VGG19 helper · level 0 · unverified · 0122d0f23bd245a5
  21. KPN helper · level 1 · ran · 956f6a72ea5b71ed
  22. Basic helper · level 1 · ran · e6abeeabd7ed1930

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="2203.06304") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image InpaintingImage RestorationSSIMVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Inpainting

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