Papers › Image Inpainting for Irregular Holes Using Partial Convolutions

Image Inpainting for Irregular Holes Using Partial Convolutions

20 Apr 2018ECCV 2018 9arXiv:1804.07723archive 2025-07-28

Guilin Liu, Fitsum A. Reda, Kevin J. Shih, Ting-Chun Wang, Andrew Tao, Bryan Catanzaro

Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value). This often leads to artifacts such as color discrepancy and blurriness. Post-processing is usually used to reduce such artifacts, but are expensive and may fail. We propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with other methods to validate our approach.

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

The archive's official repository (NVIDIA/partialconv) was not harvested; the 30 samples below come from 9 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 31 code samples: 30 from 9 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 31: 29 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 3 honoured, 1 violated, 19 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 30 samples from 9 repositories, 28 ran (23 with no instrument failure; 5 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

60 repositories listed; official and paper-mentioned ones first.

NVIDIA/partialconv officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
AnishWalawalkar/cs231 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
DosImpact/focusonme_core mentioned on GitHubpytorchMITSyntology: not harvested report
GabrieleMonte/CoMBInE mentioned on GitHubtfSyntology: not harvested report
IsHYuhi/Image_Inpainting_Using_Partial_Convolutions mentioned on GitHubpytorchSyntology: not harvested report
KPMG-wiseuniv/AI mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
King-HAW/CT_inpainting mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
KumapowerLIU/CSA-inpainting mentioned on GitHubpytorchSyntology: not harvested report
KumapowerLIU/DeFLOCNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeFLOCNet: Deep Image Editing via Flexible Low-level Controls (arXiv:2103.12723; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
KumapowerLIU/PD-GAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PD-GAN: Probabilistic Diverse GAN for Image Inpainting (arXiv:2105.02201; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
KumapowerLIU/Rethinking-Inpainting-MEDFE mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Maouriyan/inpainting_demo mentioned on GitHubpytorchSyntology: not harvested report
MathiasGruber/PConv-Keras mentioned on GitHubpytorchMITSyntology: not harvested report
NiceRingNode/Inpainting-Cpp-Deployment mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
Oorgien/Scene-Inpainting mentioned on GitHubpytorchSyntology: not harvested report
RenYurui/StructureFlow mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
SeitaroShinagawa/chainer-partial_convolution_image_inpainting mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
SimonDele/School-projects mentioned on GitHubSyntology: not harvested report
SunnerLi/P-Conv mentioned on GitHubpytorchSyntology: not harvested report
TrinhQuocNguyen/Edited_PConv-Keras mentioned on GitHubMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
WendongZh/SPL mentioned on GitHubpytorchSyntology: not harvested report
YB221/Image-Inpainting-using-Partial-Convolutional-Layers mentioned on GitHubtfSyntology: not harvested report
YaN9-Y/lafin mentioned on GitHubpytorchSyntology: not harvested report
YeshengSu/EdgeConnect mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (arXiv:1901.00212; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
anushkaw055/Image-Inpainting mentioned on GitHubpytorchSyntology: not harvested report
bobqywei/inpainting-partial-conv mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cameltr/rgtsi mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
cameltr/transref mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
chefpr7/Image-Inpainting-using-Partial-Convolutional-Layers mentioned on GitHubtfSyntology: not harvested report
devansh20la/Image_inpainting mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
diff7/pconv_hprotein mentioned on GitHubpytorchSyntology: not harvested report
dnwjddl/Inpainting mentioned on GitHubSyntology: not harvested report
feixuetuba/inpainting mentioned on GitHubpytorchSyntology: not harvested report
feixuetuba/inpating mentioned on GitHubpytorchSyntology: not harvested report
gmin7/pconv_implementation mentioned on GitHubpytorchSyntology: not harvested report
hawkit/edge-tst mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
hiyaroy12/DFT_inpainting mentioned on GitHubpytorchSyntology: not harvested report
hz-ants/edge-connect mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
joshilp/ImageInpainting mentioned on GitHubtfSyntology: not harvested report
jshi31/edge-connect mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
karfly/qd-imd mentioned on GitHubMITSyntology: not harvested report
lewisluk/PartialConvUnet mentioned on GitHubtfSyntology: not harvested report
menon92/Python-Learning mentioned on GitHubtfSyntology: not harvested report
miguel-rodrigo/dot-csv-pix2pix mentioned on GitHubtfSyntology: not harvested report
mojc/GAN_lesion_filling mentioned on GitHubSyntology: not harvested report
naoto0804/pytorch-inpainting-with-partial-conv mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (2 instrument-failed) · 0 unverified report
nekitmm/PConv_TF2.0 mentioned on GitHubtfMITSyntology: not harvested report
preeti-2810/object-removal mentioned on GitHubpytorchMITSyntology: not harvested report
rain58/boundary-aware-image-inpainting mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DIODE: A Dense Indoor and Outdoor DEpth Dataset (arXiv:1908.00463; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
singhrk45/Object-Removal-Image-inpainting- mentioned on GitHubpytorchMITSyntology: not harvested report
waallf/edge-connect-master mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
wendongzh/spn mentioned on GitHubpytorchSyntology: not harvested report
xiefan-guo/ctsdg mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Image Inpainting via Conditional Texture and Structure Dual Generation (arXiv:2108.09760; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
xkp793003821/PConv-Keras mentioned on GitHubpytorchMITSyntology: not harvested report
yashk2000/SneakySketchers mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
youyuge34/AnimeInPaint mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
2023-MindSpore-1/ms-code-210 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code7 mindsporeSyntology: not harvested report
ayulockin/deepimageinpainting tfSyntology: not harvested report
maruru-hub/PartialConv-paddle paddleMITSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

31 samples harvested: 29 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 3 honoured, 1 violated, 19 with no contract checked; 6 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
2ran; the contract check could not run
19ran
2unverified

Licence: 4 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 9 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. 1 sample is listed last, in a group without a repository. “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.

King-HAW/CT_inpainting community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
random_mask in 13 papers libs/util.py ran MIT (permissive) · b40728d4612d7b4a · report fixture: signature height:int/0/int, width:int/0/int, channels:int/0/int · returned ndarray · level recorded 2026-09-26
random_mask_line_for_ct libs/util.py ran MIT (permissive) · 733d83088fe34603 · report fixture: signature height:int/0/int, width:int/0/int, channels:int/0/int · returned ndarray · level recorded 2026-09-26
random_mask_rectangle libs/util.py unverified MIT (permissive) · d494001767883afe · report
SeitaroShinagawa/chainer-partial_convolution_image_inpainting community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
array_to_img generate_windows.py ran · honoured contract MIT (permissive) · c63bfabb83547f08 · report fixture: signature im:ndarray/2/float · returned Image · level recorded 2026-09-22
clip in 31 papers generate_windows.py ran · honoured contract fingerprinted MIT (permissive) · 126fbb3bbd63ad67 · report fixture: signature a:int/0/int · returned int · level recorded 2026-09-22
pos_clip generate_windows.py ran · honoured contract fingerprinted MIT (permissive) · 936e38231c8a7aa7 · report fixture: signature x:int/0/int, img_size:int/0/int · returned int · level recorded 2026-09-22
TrinhQuocNguyen/Edited_PConv-Keras community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
count_nonblack_np libs/util.py ran MIT (permissive) · e02610738bfdc267 · report fixture: signature img:ndarray/3/int · returned float64 · level recorded 2026-09-26
random_mask in 13 papers libs/util.py ran MIT (permissive) · 256be19ab72d51a4 · report fixture: signature height:int/0/int, width:int/0/int, channels:int/0/int · returned ndarray · level recorded 2026-09-26
random_mask_rectangles libs/util.py ran MIT (permissive) · aa6d10069438a1c5 · report fixture: signature height:int/0/int, width:int/0/int, channels:int/0/int, percent_from:float/0/float, percent_to:float/0/float, only_rec:bool/0/bool, short_rec:bool/0/bool · returned ndarray · level recorded 2026-09-26
bobqywei/inpainting-partial-conv community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
exceeds_bounds inpaint.py ran · violated contract fingerprinted no licence file found · pointer only · 66b365b2efae78bf · report fixture: signature y:int/0/int · returned bool · level recorded 2026-09-22
cameltr/rgtsi community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
get_norm_layer in 111 papers models/networks.py ran Apache-2.0 (permissive) · 5daad5c7af1b1741 · report fixture: signature norm_type:str/0/str · returned partial · level recorded 2026-09-26
get_scheduler in 122 papers models/networks.py ran Apache-2.0 (permissive) · d2575c24d11029c0 · report fixture: signature optimizer:Adam/0/?, opt:OptConfig/0/? · returned LambdaLR · level recorded 2026-09-24
init_net in 47 papers models/networks.py ran Apache-2.0 (permissive) · 64cdaca975e8a365 · report fixture: signature net:callable/0/?, init_type:str/0/str, init_gain:float/0/float, gpu_ids:list/1/empty · returned SimpleNet · level recorded 2026-09-26
spectral_norm in 42 papers models/Discriminator.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · b189ed0149b76880 · report
cameltr/transref community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
DOE_downsample_block models/RefPA/Model_utils.py ran Apache-2.0 (permissive) · d329ea45f095b88a · report fixture: signature input_channelsize:int/0/int · returned Sequential · level recorded 2026-09-26
equal_lr in 11 papers models/base_networks.py ran · our draft was wrong Apache-2.0 (permissive) · 5ef2eff36d9c9c0e · report fixture: signature module:callable/0/?, name:str/0/str · returned SimpleModule · level recorded 2026-09-22
make_downsampling_network models/RefPA/Model_utils.py ran Apache-2.0 (permissive) · 53fc335094a0c681 · report fixture: signature layernum:int/0/int, in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-26
make_residual_block models/RefPA/Model_utils.py ran Apache-2.0 (permissive) · 5e4921b68598512f · report fixture: signature blocknum:int/0/int, input_channel:int/0/int, output_channel:int/0/int, bias:bool/0/bool · returned Sequential · level recorded 2026-09-26
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models/TransRef.py ran Apache-2.0 (permissive) · 5d7bf5f17f71b491 · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/?, warning:bool/0/bool · returned Tensor · level recorded 2026-09-26
devansh20la/Image_inpainting community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
percept_style_loss Train_Gen.py ran · our draft was wrong no licence file found · pointer only · 546499c4d5f6e29a · report fixture: signature vgg:callable/0/?, L1loss:callable/0/?, x:Tensor/4/float, target:Tensor/4/float · returned tuple · level recorded 2026-09-22
naoto0804/pytorch-inpainting-with-partial-conv community (archive-listed) 6 samples, 6 ran (2 instrument-failed) · 0 unverified
get_state_dict_on_cpu util/io.py ran MIT (permissive) · c333d34b2f3803eb · report fixture: signature obj:callable/0/? · returned OrderedDict · level recorded 2026-09-25
gram_matrix in 45 papers
census: 7 implementations from 9 papers, 4 distinct outputs on one shared input
loss.py ran fingerprinted MIT (permissive) · 1715f300a6a58899 · report fixture: signature feat:Tensor/4/float · returned Tensor · level recorded 2026-09-25
load_ckpt in 31 papers util/io.py ran MIT (permissive) · 6494155d4a61448e · report fixture: signature ckpt_name:str/0/str, models:list/1/tuple, optimizers:list/1/tuple · returned int · level recorded 2026-09-25
random_walk in 12 papers generate_data.py ran fingerprinted MIT (permissive) · 1b25a2d389331946 · report fixture: signature canvas:ndarray/2/float, ini_x:int/0/int, ini_y:int/0/int, length:int/0/int · returned ndarray · level recorded 2026-09-26
total_variation_loss in 18 papers loss.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · dedfa1b69056bdc7 · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-26
weights_init in 44 papers net.py ran · our draft was wrong MIT (permissive) · b0a0259ffdb9c7d8 · report fixture: signature init_type:str/0/str · returned function · level recorded 2026-09-26
yashk2000/SneakySketchers community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
conf_to_param inpainting/utilities.py ran Apache-2.0 (permissive) · 5159f16354d4577b · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-26
dialation_holes inpainting/loss.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 5e14b9034e5790ba · report fixture: signature hole_mask:Tensor/4/float · returned Tensor · level recorded 2026-09-22
to_items inpainting/utilities.py ran Apache-2.0 (permissive) · 79d7b29bdb460a4f · report fixture: signature dic:dict/0/? · returned dict · level recorded 2026-09-25
total_variation_loss in 18 papers inpainting/loss.py ran fingerprinted Apache-2.0 (permissive) · 48322e1ae6659815 · report fixture: signature image:Tensor/4/float, mask:Tensor/4/float, method:str/0/str · returned Tensor · level recorded 2026-09-26
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
gram_matrix in 45 papers
census: 7 implementations from 9 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 1090950b58e9358b · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22

Tasks

Image Inpainting

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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