Papers › Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame...

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

1 Mar 2023CVPR 2023 1arXiv:2303.00440archive 2025-07-28

Guozhen Zhang, Yuhan Zhu, Haonan Wang, Youxin Chen, Gangshan Wu, LiMin Wang

Effectively extracting inter-frame motion and appearance information is important for video frame interpolation (VFI). Previous works either extract both types of information in a mixed way or elaborate separate modules for each type of information, which lead to representation ambiguity and low efficiency. In this paper, we propose a novel module to explicitly extract motion and appearance information via a unifying operation. Specifically, we rethink the information process in inter-frame attention and reuse its attention map for both appearance feature enhancement and motion information extraction. Furthermore, for efficient VFI, our proposed module could be seamlessly integrated into a hybrid CNN and Transformer architecture. This hybrid pipeline can alleviate the computational complexity of inter-frame attention as well as preserve detailed low-level structure information. Experimental results demonstrate that, for both fixed- and arbitrary-timestep interpolation, our method achieves state-of-the-art performance on various datasets. Meanwhile, our approach enjoys a lighter computation overhead over models with close performance. The source code and models are available at https://github.com/MCG-NJU/EMA-VFI.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 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: 12 samples from 1 repository, 10 ran (6 with no instrument failure; 4 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/ema-vfi officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 10 ran (4 instrument-failed) · 2 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

12 samples harvested: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
2ran; the contract check could not run
6ran
2unverified

Licence: 0 of the 12 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/ema-vfi. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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/ema-vfi official repository 12 samples, 10 ran (4 instrument-failed) · 2 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
model/feature_extractor.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a9f0972fc8d657ae · report fixture: returned ConvBlock · level recorded 2026-09-22
CrossScalePatchEmbed model/feature_extractor.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 4d87dd873dd0cb76 · report fixture: returned CrossScalePatchEmbed · level recorded 2026-09-22
DWConv in 14 papers model/feature_extractor.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b5607e4cc9098c21 · report fixture: returned DWConv · level recorded 2026-09-22
InterFrameAttention model/feature_extractor.py ran Apache-2.0 (permissive) · 5d39fa7b2acea443 · report fixture: signature x1:Tensor/3/float, x2:Tensor/3/float, cor:Tensor/3/float, H:int/0/int, W:int/0/int, mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
Mlp in 102 papers model/feature_extractor.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 49e7751169736ead · report fixture: returned Mlp · level recorded 2026-09-22
OverlapPatchEmbed in 16 papers model/feature_extractor.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · bc9aa8676665e403 · report fixture: returned OverlapPatchEmbed · level recorded 2026-09-22
depad_if_needed model/feature_extractor.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · def44daa823d60b3 · report fixture: signature x:Tensor/4/float, size:tuple/1/int, window_size:tuple/1/int · returned Tensor · level recorded 2026-09-22
pad_if_needed in 5 papers model/feature_extractor.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · aa39c3cb6f9a4cb6 · report fixture: signature x:Tensor/4/float, size:tuple/1/int, window_size:tuple/1/int · returned tuple · level recorded 2026-09-22
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model/feature_extractor.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 9641bf1050805151 · report fixture: signature x:Tensor/4/float, window_size:list/1/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers model/feature_extractor.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 4b2da073b4d351d3 · report fixture: signature windows:Tensor/3/float, window_size:tuple/1/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
MotionFormer model/feature_extractor.py unverified Apache-2.0 (permissive) · faa0a3a2edc81e48 · report
MotionFormerBlock model/feature_extractor.py unverified Apache-2.0 (permissive) · e3645b81274cf177 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for EMA-VFI (graph method: EMA-VFI). 12 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. MotionFormer entry · level 0 · unverified · faa0a3a2edc81e48
  2. ConvBlock helper · level 1 · ran · a9f0972fc8d657ae
  3. CrossScalePatchEmbed model · level 1 · ran · 4d87dd873dd0cb76
  4. MotionFormerBlock model · level 0 · unverified · e3645b81274cf177
  5. OverlapPatchEmbed model · level 1 · ran · bc9aa8676665e403
  6. InterFrameAttention model · level 1 · ran · 5d39fa7b2acea443
  7. Mlp model · level 1 · ran · 49e7751169736ead
  8. depad_if_needed helper · level 1 · ran · our draft was wrong · def44daa823d60b3
  9. pad_if_needed helper · level 1 · ran · our draft was wrong · aa39c3cb6f9a4cb6
  10. window_partition helper · level 1 · ran; the contract check could not run (RAISES) · 9641bf1050805151
  11. window_reverse helper · level 1 · ran; the contract check could not run (RAISES) · 4b2da073b4d351d3
  12. DWConv model · level 1 · ran · b5607e4cc9098c21

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.00440") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Video Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation MSU Video Frame Interpolation EMA-VFI LPIPS 0.022 #4 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EMA-VFI MS-SSIM 0.965 #4 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EMA-VFI PSNR 29.89 #4 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EMA-VFI SSIM 0.953 #4 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation EMA-VFI VMAF 71.71 #4 of 24 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) EMA-VFI PSNR 39.98 #7 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (easy) EMA-VFI SSIM 0.9910 #7 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) EMA-VFI PSNR 25.69 #4 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (extreme) EMA-VFI SSIM 0.8661 #4 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) EMA-VFI PSNR 30.94 #4 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (hard) EMA-VFI SSIM 0.9392 #4 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) EMA-VFI PSNR 36.09 #6 of 8 Archive leaderboard report
Video Frame Interpolation SNU-FILM (medium) EMA-VFI SSIM 0.9801 #6 of 8 Archive leaderboard report
Video Frame Interpolation UCF101 EMA-VFI PSNR 35.48 #1 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 EMA-VFI SSIM 0.9701 #1 of 19 Archive leaderboard report
Video Frame Interpolation Vimeo90K EMA-VFI PSNR 36.64 #2 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K EMA-VFI SSIM 0.9819 #2 of 23 Archive leaderboard report
Video Frame Interpolation X4K1000FPS EMA-VFI PSNR 31.46 #5 of 20 Archive leaderboard report
Video Frame Interpolation X4K1000FPS-2K EMA-VFI PSNR 32.85 #2 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K EMA-VFI PSNR 36.90 #2 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K EMA-VFI SSIM 0.945 #2 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-4k EMA-VFI PSNR 34.67 #1 of 3 Archive leaderboard report
Video Frame Interpolation Xiph-4k EMA-VFI SSIM 0.907 #1 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

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