Papers › VFIMamba: Video Frame Interpolation with State Space Models

VFIMamba: Video Frame Interpolation with State Space Models

2 Jul 2024arXiv:2407.02315archive 2025-07-28

Guozhen Zhang, Chunxu Liu, Yutao Cui, Xiaotong Zhao, Kai Ma, LiMin Wang

Inter-frame modeling is pivotal in generating intermediate frames for video frame interpolation (VFI). Current approaches predominantly rely on convolution or attention-based models, which often either lack sufficient receptive fields or entail significant computational overheads. Recently, Selective State Space Models (S6) have emerged, tailored specifically for long sequence modeling, offering both linear complexity and data-dependent modeling capabilities. In this paper, we propose VFIMamba, a novel frame interpolation method for efficient and dynamic inter-frame modeling by harnessing the S6 model. Our approach introduces the Mixed-SSM Block (MSB), which initially rearranges tokens from adjacent frames in an interleaved fashion and subsequently applies multi-directional S6 modeling. This design facilitates the efficient transmission of information across frames while upholding linear complexity. Furthermore, we introduce a novel curriculum learning strategy that progressively cultivates proficiency in modeling inter-frame dynamics across varying motion magnitudes, fully unleashing the potential of the S6 model. Experimental findings showcase that our method attains state-of-the-art performance across diverse benchmarks, particularly excelling in high-resolution scenarios. In particular, on the X-TEST dataset, VFIMamba demonstrates a noteworthy improvement of 0.80 dB for 4K frames and 0.96 dB for 2K frames.

PaperPDFCodeCode 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

Syntology 8 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 3 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: official repository: 8 samples from 1 repository, 8 ran (3 with no instrument failure; 5 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mcg-nju/vfimamba officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 8 ran (5 instrument-failed) · 0 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

8 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 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
3ran · our draft was wrong
2ran; the contract check could not run
2ran

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 mcg-nju/vfimamba. “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.

mcg-nju/vfimamba official repository 8 samples, 8 ran (5 instrument-failed) · 0 unverified
conv in 178 papers model/feature_extractor.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 1d13034a9dbf1c2a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int · returned Sequential · level recorded 2026-09-22
convert in 76 papers Trainer_finetune.py ran · our draft was wrong Apache-2.0 (permissive) · 3466e04858238f2e · report fixture: signature param:dict/0/? · returned dict · level recorded 2026-09-24
deconv in 48 papers model/refine.py ran Apache-2.0 (permissive) · 23f41c2655d6295a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int · returned Sequential · level recorded 2026-09-24
downsample in 59 papers model/loss.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 1f6001e1c3b06556 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
gauss_kernel in 15 papers model/loss.py ran · honoured contract Apache-2.0 (permissive) · 337a38a7be8077eb · report fixture: signature channels:int/0/int · returned Tensor · level recorded 2026-09-24
init_model_config config.py ran Apache-2.0 (permissive) · a21dfbe077bf6da8 · report fixture: signature F:int/0/int, W:int/0/int, depth:list/1/int, M:bool/0/bool · returned tuple · level recorded 2026-09-24
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
model/loss.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 23101166bb29f65e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
warp in 27 papers model/warplayer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 662710159b487a9d · report fixture: signature tenInput:Tensor/4/float, tenFlow:Tensor/4/float · returned Tensor · level recorded 2026-09-24

Tasks

2k4kState Space ModelsVideo Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation SNU-FILM (easy) VFIMamba PSNR 40.51 #2 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) VFIMamba SSIM 0.9912 #2 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) VFIMamba PSNR 25.79 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) VFIMamba SSIM 0.8682 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) VFIMamba PSNR 30.99 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) VFIMamba SSIM 0.9401 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) VFIMamba PSNR 36.40 #3 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) VFIMamba SSIM 0.9805 #3 of 8 Archive leaderboard report
Video Frame Interpolation UCF101 VFIMamba PSNR 35.45 #3 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 VFIMamba SSIM 0.9702 #3 of 19 Archive leaderboard report
Video Frame Interpolation X4K1000FPS VFIMamba PSNR 32.15 #3 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS VFIMamba SSIM 0.9246 #3 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS-2K VFIMamba PSNR 33.33 #1 of 4 Archive leaderboard report
Video Frame Interpolation X4K1000FPS-2K VFIMamba SSIM 0.9362 #1 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K VFIMamba PSNR 37.13 #1 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K VFIMamba SSIM 0.9451 #1 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-4k VFIMamba PSNR 34.62 #2 of 3 Archive leaderboard report
Video Frame Interpolation Xiph-4k VFIMamba SSIM 0.9059 #2 of 3 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

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