Papers › FILM: Frame Interpolation for Large Motion

FILM: Frame Interpolation for Large Motion

10 Feb 2022arXiv:2202.04901archive 2025-07-28

Fitsum Reda, Janne Kontkanen, Eric Tabellion, Deqing Sun, Caroline Pantofaru, Brian Curless

We present a frame interpolation algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Recent methods use multiple networks to estimate optical flow or depth and a separate network dedicated to frame synthesis. This is often complex and requires scarce optical flow or depth ground-truth. In this work, we present a single unified network, distinguished by a multi-scale feature extractor that shares weights at all scales, and is trainable from frames alone. To synthesize crisp and pleasing frames, we propose to optimize our network with the Gram matrix loss that measures the correlation difference between feature maps. Our approach outperforms state-of-the-art methods on the Xiph large motion benchmark. We also achieve higher scores on Vimeo-90K, Middlebury and UCF101, when comparing to methods that use perceptual losses. We study the effect of weight sharing and of training with datasets of increasing motion range. Finally, we demonstrate our model's effectiveness in synthesizing high quality and temporally coherent videos on a challenging near-duplicate photos dataset. Codes and pre-trained models are available at https://film-net.github.io.

PaperPDFCodeCode 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 20 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 14 samples from 1 repository, 10 ran (7 with no instrument failure; 3 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.

google-research/frame-interpolation officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
dajes/frame-interpolation-pytorch pytorchSyntology: 14 samples, 10 ran (3 instrument-failed) · 4 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

20 samples harvested: 12 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 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.

1ran · honoured contract
3ran · our draft was wrong
8ran
8unverified

Licence: 0 of the 20 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 1 sample 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.

google-research/frame-interpolation official repository 6 samples, 2 ran (0 instrument-failed) · 4 unverified
l1_loss in 149 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
losses/losses.py ran Apache-2.0 (permissive) · 36bbb37e74c4a4dc · report fixture: signature example:dict/0/?, prediction:dict/0/? · returned EagerTensor · level recorded 2026-09-24
patches_to_image eval/interpolator.py ran Apache-2.0 (permissive) · 41eb7c711cf87551 · report fixture: signature patches:ndarray/4/float, block_shape:list/1/int · returned ndarray · level recorded 2026-09-24
generate_image_triplet_example datasets/util.py unverified Apache-2.0 (permissive) · 62b36be97a57cd56 · report
image_to_patches eval/interpolator.py unverified Apache-2.0 (permissive) · 81e6e74325f0e8ca · report
style_loss losses/vgg19_loss.py unverified Apache-2.0 (permissive) · c4b4c0fc22dc8ce1 · report
vgg_loss losses/vgg19_loss.py unverified Apache-2.0 (permissive) · 56ee3540e67f1685 · report
dajes/frame-interpolation-pytorch community (archive-listed) 14 samples, 10 ran (3 instrument-failed) · 4 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
interpolator.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 33031ed5f24825b1 · report fixture: returned Conv2d · level recorded 2026-09-22
FeatureExtractor in 24 papers interpolator.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 9ef67e49992f642f · report fixture: returned FeatureExtractor · level recorded 2026-09-22
FlowEstimator interpolator.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a7349eca770ecdf9 · report fixture: returned FlowEstimator · level recorded 2026-09-22
Fusion in 6 papers interpolator.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 5df4eeacc27fbe49 · report fixture: returned Fusion · level recorded 2026-09-22
PyramidFlowEstimator interpolator.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 646c00a2c3ce3ec0 · report fixture: returned PyramidFlowEstimator · level recorded 2026-09-22
SubTreeExtractor interpolator.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · c47da384c303149c · report fixture: returned SubTreeExtractor · level recorded 2026-09-22
build_image_pyramid interpolator.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5e996c1e85b97cc1 · report fixture: signature image:Tensor/4/float, pyramid_levels:int/0/int · returned list · level recorded 2026-09-22
concatenate_pyramids interpolator.py ran · our draft was wrong Apache-2.0 (permissive) · e5a70acb4070eb0f · report fixture: signature pyramid1:list/1/Tensor, pyramid2:list/1/Tensor · returned list · level recorded 2026-09-22
flow_pyramid_synthesis interpolator.py ran · our draft was wrong Apache-2.0 (permissive) · 6ea74e810cda7a86 · report fixture: signature residual_pyramid:list/1/Tensor · returned list · level recorded 2026-09-22
get_channels_at_level interpolator.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · f8ee6422386d84b6 · report fixture: signature level:int/0/int, filters:int/0/int · returned int · level recorded 2026-09-22
Interpolator interpolator.py unverified Apache-2.0 (permissive) · e48dec25e2c77c29 · report
multiply_pyramid interpolator.py unverified Apache-2.0 (permissive) · 12d32fa9bc246c8f · report
pyramid_warp interpolator.py unverified Apache-2.0 (permissive) · 6c403027f71d5c0e · report
warp in 27 papers interpolator.py unverified Apache-2.0 (permissive) · b6d4f892f64d3fe9 · 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 FILM (graph method: FILM). 14 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. Interpolator entry · level 0 · unverified · e48dec25e2c77c29
  2. FeatureExtractor model · level 1 · ran · 9ef67e49992f642f
  3. Fusion model · level 1 · ran · 5df4eeacc27fbe49
  4. PyramidFlowEstimator model · level 1 · ran · 646c00a2c3ce3ec0
  5. build_image_pyramid helper · level 1 · ran · our draft was wrong · 5e996c1e85b97cc1
  6. concatenate_pyramids helper · level 1 · ran · our draft was wrong · e5a70acb4070eb0f
  7. flow_pyramid_synthesis helper · level 1 · ran · our draft was wrong · 6ea74e810cda7a86
  8. multiply_pyramid helper · level 0 · unverified · 12d32fa9bc246c8f
  9. pyramid_warp helper · level 0 · unverified · 6c403027f71d5c0e
  10. SubTreeExtractor helper · level 1 · ran · c47da384c303149c
  11. Conv2d helper · level 1 · ran · 33031ed5f24825b1
  12. get_channels_at_level helper · level 1 · ran · honoured contract · f8ee6422386d84b6
  13. FlowEstimator helper · level 1 · ran · a7349eca770ecdf9
  14. warp helper · level 0 · unverified · b6d4f892f64d3fe9

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="2202.04901") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Optical Flow EstimationVideo Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation MSU Video Frame Interpolation FILM LPIPS 0.033 #10 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FILM MS-SSIM 0.948 #10 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FILM PSNR 28.11 #10 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FILM SSIM 0.928 #10 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation FILM VMAF 68.68 #10 of 24 Archive leaderboard report
Video Frame Interpolation Middlebury FILM PSNR 37.52 #10 of 11 Archive leaderboard report
Video Frame Interpolation Middlebury FILM SSIM 0.966 #10 of 11 Archive leaderboard report
Video Frame Interpolation UCF101 FILM PSNR 35.32 #12 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 FILM SSIM 0.952 #12 of 19 Archive leaderboard report
Video Frame Interpolation Vimeo90K FILM PSNR 36.06 #9 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K FILM SSIM 0.97 #9 of 23 Archive leaderboard report
Video Frame Interpolation Xiph-2K FILM PSNR 36.66 #3 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-2K FILM SSIM 0.951 #3 of 4 Archive leaderboard report
Video Frame Interpolation Xiph-4k FILM PSNR 33.78 #3 of 3 Archive leaderboard report
Video Frame Interpolation Xiph-4k FILM SSIM 0.906 #3 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.

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