Papers › Learning Joint Spatial-Temporal Transformations for Video Inpainting

Learning Joint Spatial-Temporal Transformations for Video Inpainting

20 Jul 2020ECCV 2020 8arXiv:2007.10247archive 2025-07-28

Yanhong Zeng, Jianlong Fu, Hongyang Chao

High-quality video inpainting that completes missing regions in video frames is a promising yet challenging task. State-of-the-art approaches adopt attention models to complete a frame by searching missing contents from reference frames, and further complete whole videos frame by frame. However, these approaches can suffer from inconsistent attention results along spatial and temporal dimensions, which often leads to blurriness and temporal artifacts in videos. In this paper, we propose to learn a joint Spatial-Temporal Transformer Network (STTN) for video inpainting. Specifically, we simultaneously fill missing regions in all input frames by self-attention, and propose to optimize STTN by a spatial-temporal adversarial loss. To show the superiority of the proposed model, we conduct both quantitative and qualitative evaluations by using standard stationary masks and more realistic moving object masks. Demo videos are available at https://github.com/researchmm/STTN.

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="2007.10247")

Code

Syntology Ran 1 of 7 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 7 samples from 1 repository, 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.

researchmm/STTN officialmentioned in papermentioned on GitHubpytorchMIT report
Feynman1999/MgeEditing mentioned on GitHub 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 · fixture could not drive it
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 researchmm/STTN. “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.

random_accelerate researchmm/STTN/core/utils.py official repository ran · fixture could not drive it MIT (permissive) · d98f6e80e969ffbd · report
create_random_shape_with_random_motion researchmm/STTN/core/utils.py official repository unverified MIT (permissive) · 30f35d199c193fbe · report
get_random_shape researchmm/STTN/core/utils.py official repository unverified MIT (permissive) · 6377912546960040 · report
get_ref_index researchmm/STTN/core/dataset.py official repository unverified MIT (permissive) · 460140ea6a070542 · report
remove_spectral_norm researchmm/STTN/core/spectral_norm.py official repository unverified MIT (permissive) · 5db67c73b56c8cd0 · report
spectral_norm researchmm/STTN/core/spectral_norm.py official repository unverified MIT (permissive) · 2fbfa7555a2ca4af · report
use_spectral_norm researchmm/STTN/core/spectral_norm.py official repository unverified MIT (permissive) · b674053606e02d7e · report

Tasks

Seeing Beyond the VisibleVideo Inpainting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Seeing Beyond the Visible KITTI360-EX STTN Average PSNR 18.73 #5 of 7 Archive leaderboard report
Video Inpainting DAVIS STTN Ewarp 0.1449 #5 of 11 Archive leaderboard report
Video Inpainting DAVIS STTN PSNR 30.67 #5 of 11 Archive leaderboard report
Video Inpainting DAVIS STTN SSIM 0.9560 #5 of 11 Archive leaderboard report
Video Inpainting DAVIS STTN VFID 0.149 #5 of 11 Archive leaderboard report
Video Inpainting HQVI (240p) STTN LPIPS 0.0528 #7 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) STTN PSNR 29.64 #7 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) STTN SSIM 0.9339 #7 of 7 Archive leaderboard report
Video Inpainting HQVI (240p) STTN VFID 0.2594 #7 of 7 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 STTN Ewarp 0.0907 #5 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 STTN PSNR 32.34 #5 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 STTN SSIM 0.9655 #5 of 10 Archive leaderboard report
Video Inpainting YouTube-VOS 2018 STTN VFID 0.053 #5 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 ConnectionsDropoutLabel 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