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 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="2407.02315")

Code

Syntology Ran 8 of 8 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mcg-nju/vfimamba officialmentioned in papermentioned on GitHubpytorchApache-2.0 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; 0 honoured the contract we drafted; 0 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
7ran

Licence: 0 of the 8 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 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. “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.

conv mcg-nju/vfimamba/model/feature_extractor.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 1d13034a9dbf1c2a · report
convert mcg-nju/vfimamba/Trainer_finetune.py official repository ran Apache-2.0 (permissive) · 3466e04858238f2e · report
deconv mcg-nju/vfimamba/model/refine.py official repository ran Apache-2.0 (permissive) · 23f41c2655d6295a · report
downsample mcg-nju/vfimamba/model/loss.py official repository ran fingerprinted Apache-2.0 (permissive) · 1f6001e1c3b06556 · report
gauss_kernel mcg-nju/vfimamba/model/loss.py official repository ran Apache-2.0 (permissive) · 337a38a7be8077eb · report
init_model_config mcg-nju/vfimamba/config.py official repository ran Apache-2.0 (permissive) · a21dfbe077bf6da8 · report
upsample mcg-nju/vfimamba/model/loss.py official repository ran fingerprinted Apache-2.0 (permissive) · 23101166bb29f65e · report
warp mcg-nju/vfimamba/model/warplayer.py official repository ran fingerprinted Apache-2.0 (permissive) · 662710159b487a9d · report

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