Papers › Free-Form Image Inpainting with Gated Convolution

Free-Form Image Inpainting with Gated Convolution

10 Jun 2018ICCV 2019 10arXiv:1806.03589archive 2025-07-28

Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas Huang

We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single rectangular mask are not applicable. Thus, we also present a patch-based GAN loss, named SN-PatchGAN, by applying spectral-normalized discriminator on dense image patches. SN-PatchGAN is simple in formulation, fast and stable in training. Results on automatic image inpainting and user-guided extension demonstrate that our system generates higher-quality and more flexible results than previous methods. Our system helps user quickly remove distracting objects, modify image layouts, clear watermarks and edit faces. Code, demo and models are available at: https://github.com/JiahuiYu/generative_inpainting

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1806.03589")

Code

Syntology Ran 1 of 7 code samples harvested from 3 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 7 samples from 3 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

JiahuiYu/generative_inpainting officialmentioned in papermentioned on GitHubtfNOASSERTION report
CS269-Capstone/t-snake-capstone mentioned on GitHubtfNOASSERTION report
CS269-Capstone/t-snake-mask-generation mentioned on GitHubtfNOASSERTION report
ChopsticksAN/generative_inpainting mentioned on GitHubtfNOASSERTION report
Ir1d/tf-models mentioned on GitHubtfNOASSERTION report
ShnitzelKiller/generative_inpainting mentioned on GitHubtfNOASSERTION report
TerminatorSd/generative mentioned on GitHubtfNOASSERTION report
avalonstrel/GatedConvolution mentioned on GitHubtfNOASSERTION report
boge8888/Watermark-removal-GUI mentioned on GitHubtfNOASSERTION report
btxuyenHCMUS/generative mentioned on GitHubtfNOASSERTION report
btxuyenHCMUS/inpainting mentioned on GitHubtfMIT report
csqiangwen/DeepFillv2_Pytorch mentioned on GitHubpytorchMIT report
feixuetuba/inpainting mentioned on GitHubpytorch report
feixuetuba/inpating mentioned on GitHubpytorch report
g2zac/generative_inpainting mentioned on GitHubtfNOASSERTION report
huynhhoanghuy/Image-Inpainting mentioned on GitHubtfNOASSERTION report
jiajunhua/JiahuiYu-generative_inpainting mentioned on GitHubtfNOASSERTION report
katychou/generative01 mentioned on GitHubtfNOASSERTION report
nipponjo/deepfillv2-pytorch mentioned on GitHubpytorch report
nuneslu/VeIGAN mentioned on GitHubtfNOASSERTION report
pfnet-research/Chainer-DeepFill mentioned on GitHubMIT report
rajprakrit/DeepFillv2 mentioned on GitHubpytorchMIT report
runze-wang-sjtu/generative_inpainting mentioned on GitHubtfNOASSERTION report
vrindaprabhu/deepfillv2_colab mentioned on GitHubpytorch report
xurongchao/mv-inpainting mentioned on GitHubtfNOASSERTION report
zuruoke/watermark-removal mentioned on GitHubtf 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

7 samples harvested; 1 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
6unverified

Licence: 0 of the 7 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

l2normalize csqiangwen/DeepFillv2_Pytorch/network_module.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · bedff51745d2cf84 · report
batch_postprocess_images pfnet-research/Chainer-DeepFill/src/utils.py community (archive-listed) unverified MIT (permissive) · 4caf963a3beebcf2 · report
bbox2mask pfnet-research/Chainer-DeepFill/src/inpaint_ops.py community (archive-listed) unverified MIT (permissive) · 74b8bbb02eed8073 · report
dataset_files SayedNadim/Free_Form_Image_Inpainting_Gated_Conv/flist_maker.py community (archive-listed) unverified MIT (permissive) · d6d0565ac9e754d3 · report
free_form_mask pfnet-research/Chainer-DeepFill/src/inpaint_ops.py community (archive-listed) unverified MIT (permissive) · 5e0f61f83bc68c0f · report
random_bbox pfnet-research/Chainer-DeepFill/src/inpaint_ops.py community (archive-listed) unverified MIT (permissive) · 06995870b9c8a9ae · report
text_readlines csqiangwen/DeepFillv2_Pytorch/utils.py community (archive-listed) unverified MIT (permissive) · 2c0f9420e07c7b34 · report

Tasks

FormImage Inpaintingfeature selection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Inpainting Places2 DeepFill v2 FID 9.27 #8 of 14 Archive leaderboard report
Image Inpainting Places2 DeepFill v2 P-IDS 4.01 #8 of 14 Archive leaderboard report
Image Inpainting Places2 DeepFill v2 U-IDS 21.32 #8 of 14 Archive leaderboard report
Image Inpainting Places2 val DeepFillv2 (20-30% free form) FID 13.5 #3 of 7 Archive leaderboard report
Image Inpainting Places2 val DeepFillv2 (20-30% free form) PD 63.0 #3 of 7 Archive leaderboard report
Image Inpainting Places2 val DeepFillv2 (128×128 center mask) FID 15.3 #5 of 7 Archive leaderboard report
Image Inpainting Places2 val DeepFillv2 (128×128 center mask) PD 96.3 #5 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionConvolutionGated ConvolutionGated Linear Unit

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