Papers › ProPainter: Improving Propagation and Transformer for Video Inpainting

ProPainter: Improving Propagation and Transformer for Video Inpainting

7 Sep 2023ICCV 2023 1arXiv:2309.03897archive 2025-07-28

Shangchen Zhou, Chongyi Li, Kelvin C. K. Chan, Chen Change Loy

Flow-based propagation and spatiotemporal Transformer are two mainstream mechanisms in video inpainting (VI). Despite the effectiveness of these components, they still suffer from some limitations that affect their performance. Previous propagation-based approaches are performed separately either in the image or feature domain. Global image propagation isolated from learning may cause spatial misalignment due to inaccurate optical flow. Moreover, memory or computational constraints limit the temporal range of feature propagation and video Transformer, preventing exploration of correspondence information from distant frames. To address these issues, we propose an improved framework, called ProPainter, which involves enhanced ProPagation and an efficient Transformer. Specifically, we introduce dual-domain propagation that combines the advantages of image and feature warping, exploiting global correspondences reliably. We also propose a mask-guided sparse video Transformer, which achieves high efficiency by discarding unnecessary and redundant tokens. With these components, ProPainter outperforms prior arts by a large margin of 1.46 dB in PSNR while maintaining appealing efficiency.

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="2309.03897")

Code

Syntology Ran 20 of 34 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run. Of those that ran: 6 ran · our draft was wrong; 2 ran · fixture could not drive it; 12 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 10 ran; community (archive-listed): 18 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sczhou/propainter officialmentioned in papermentioned on GitHubpytorch report
osmr/propainter mentioned on GitHubMIT report
osmr/pytorchcv mentioned on GitHubpytorch 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

34 samples harvested; 20 ran; 0 honoured the contract we drafted; 14 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.

6ran · our draft was wrong
2ran · fixture could not drive it
12ran
14unverified

Licence: 16 of the 34 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 2 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.

DeformableAlignment sczhou/propainter/model/propainter.py official repository ran licence not identified · pointer only · 4cdb3a50bc7f846f · report
Encoder sczhou/propainter/model/propainter.py official repository ran licence not identified · pointer only · 53a5eb8ddb64103e · report
FusionFeedForward sczhou/propainter/model/propainter.py official repository ran licence not identified · pointer only · 83d5cf110edb5af1 · report
ModulatedDeformConv2d sczhou/propainter/model/propainter.py official repository ran licence not identified · pointer only · cbeb924f2247e025 · report
SoftSplit sczhou/propainter/model/propainter.py official repository ran licence not identified · pointer only · 9ff5a33dc359eb58 · report
SparseWindowAttention sczhou/propainter/model/propainter.py official repository ran licence not identified · pointer only · c4696b981f65032e · report
fbConsistencyCheck sczhou/propainter/model/propainter.py official repository ran · our draft was wrong fingerprinted licence not identified · pointer only · e34f0d309218c4cb · report
flow_warp sczhou/propainter/model/propainter.py official repository ran · our draft was wrong licence not identified · pointer only · 0724aee9bf22b8ca · report
length_sq sczhou/propainter/model/propainter.py official repository ran · our draft was wrong fingerprinted licence not identified · pointer only · 99919ce37333a615 · report
window_partition sczhou/propainter/model/propainter.py official repository ran · fixture could not drive it licence not identified · pointer only · c384ddd8232a9399 · report
BidirectionalPropagation sczhou/propainter/model/propainter.py official repository unverified licence not identified · pointer only · a7a87d9746b62c93 · report
InpaintGenerator sczhou/propainter/model/propainter.py official repository unverified licence not identified · pointer only · 7b9c10bbcaf37395 · report
SoftComp sczhou/propainter/model/propainter.py official repository unverified licence not identified · pointer only · ae3ca4ef5eac8aec · report
TemporalSparseTransformer sczhou/propainter/model/propainter.py official repository unverified licence not identified · pointer only · 0355e712ec5750ab · report
TemporalSparseTransformerBlock sczhou/propainter/model/propainter.py official repository unverified licence not identified · pointer only · fa4fe301319a48a2 · report
constant_init sczhou/propainter/model/propainter.py official repository unverified licence not identified · pointer only · ae01e24194ffa4ed · report
FusionFeedForward osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran MIT (permissive) · 83365c19252ece6f · report
InterpolationBlock osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran fingerprinted MIT (permissive) · 2fd5dd72e6bde9a9 · report
SoftComp osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran MIT (permissive) · b4d2964f508734c3 · report
SoftSplit osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran MIT (permissive) · 7bd366ee66ea9c84 · report
SparseWindowAttention osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran MIT (permissive) · f13da9bfe053deb9 · report
fb_consistency_check osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 3d45197997a22569 · report
flow_warp osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 6dba82ef5e1d54be · report
lambda_leakyrelu osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 51f95e8de4711196 · report
lambda_tanh osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran MIT (permissive) · f2b2ee9daa61fd8a · report
window_partition osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · fe92e2df4330e9ac · report
BidirectionalPropagation osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · 1949ce12af406baf · report
Decoder osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · 40b9d090f9b5f53d · report
Encoder osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · 5c1215e3af8ca9ac · report
PPDecoderUnit osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · f84760164d9dbd1e · report
ProPainter osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · fc85da2c0e05c2ba · report
SecondOrderDeformableAlignment osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · 0abf43743d60bcbc · report
TemporalSparseTransformer osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · 3e21907371a62b09 · report
TemporalSparseTransformerBlock osmr/pytorchcv/pytorchcv/models/propainter.py community (archive-listed) unverified MIT (permissive) · c9aea7b11102c2aa · report

Tasks

Optical Flow EstimationVideo Inpainting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Inpainting HQVI (240p) ProPainter LPIPS 0.0388 #2 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) ProPainter PSNR 30.62 #2 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) ProPainter SSIM 0.9413 #2 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) ProPainter VFID 0.2128 #2 of 7 Archive leaderboard report
Video Inpainting HQVI (480p) ProPainter LPIPS 0.0457 #4 of 4 Archive leaderboard report
Video Inpainting HQVI (480p) ProPainter PSNR 30.69 #4 of 4 Archive leaderboard report
Video Inpainting HQVI (480p) ProPainter SSIM 0.9414 #4 of 4 Archive leaderboard report
Video Inpainting HQVI (480p) ProPainter VFID 0.0478 #4 of 4 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 ProPainter Ewarp - #1 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 ProPainter PSNR 34.43 #1 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 ProPainter SSIM 0.9735 #1 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 ProPainter VFID 0.042 #1 of 10 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutInpaintingLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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