Papers › IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

29 May 2022CVPR 2022 1arXiv:2205.14620archive 2025-07-28

Lingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu, Xiaoming Huang, Ying Tai, Chengjie Wang, Jie Yang

Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications. In this work, we devise an efficient encoder-decoder based network, termed IFRNet, for fast intermediate frame synthesizing. It first extracts pyramid features from given inputs, and then refines the bilateral intermediate flow fields together with a powerful intermediate feature until generating the desired output. The gradually refined intermediate feature can not only facilitate intermediate flow estimation, but also compensate for contextual details, making IFRNet do not need additional synthesis or refinement module. To fully release its potential, we further propose a novel task-oriented optical flow distillation loss to focus on learning the useful teacher knowledge towards frame synthesizing. Meanwhile, a new geometry consistency regularization term is imposed on the gradually refined intermediate features to keep better structure layout. Experiments on various benchmarks demonstrate the excellent performance and fast inference speed of proposed approaches. Code is available at https://github.com/ltkong218/IFRNet.

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 20 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 3 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: 10 samples from 1 repository, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 10 samples from 1 repository, 7 ran (4 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. 1 of the 17 samples that ran has no recorded date.

ltkong218/ifrnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 10 ran (1 instrument-failed) · 0 unverified report
pilot7747/sldl pytorchSyntology: 10 samples, 7 ran (3 instrument-failed) · 3 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: 17 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 3 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
2ran · our draft was wrong
2ran; the contract check could not run
12ran
3unverified

Licence: 1 of the 20 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 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.

ltkong218/ifrnet official repository 10 samples, 10 ran (1 instrument-failed) · 0 unverified
create_window in 82 papers metric.py ran fingerprinted MIT (permissive) · ddde98d185346197 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-24
create_window_3d metric.py ran MIT (permissive) · 44cbb53da2e7f168 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-24
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
metric.py ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
get_lr in 91 papers train_gopro.py ran MIT (permissive) · aaa35a6320121aa6 · report fixture: signature args:ArgsConfig/0/?, iters:int/0/int · returned float64 · level recorded 2026-09-24
get_robust_weight utils.py ran fingerprinted MIT (permissive) · 4dc728d7076fe0a9 · report fixture: signature flow_pred:Tensor/4/float, flow_gt:Tensor/4/float, beta:float/0/float · returned Tensor · level recorded 2026-09-24
random_crop in 59 papers datasets.py ran MIT (permissive) · 25081efb127925fd · report fixture: signature img0:ndarray/3/int, imgt:ndarray/3/int, img1:ndarray/3/int, flow:ndarray/3/float, crop_size:tuple/1/int · returned tuple · level recorded 2026-09-24
random_resize datasets.py ran MIT (permissive) · b17c1ca578cfa57d · report fixture: signature img0:ndarray/3/int, imgt:ndarray/3/int, img1:ndarray/3/int, flow:ndarray/3/float, p:float/0/float · returned tuple · level recorded 2026-09-24
random_reverse_channel datasets.py ran MIT (permissive) · 04cda3b8b4206a50 · report fixture: signature img0:ndarray/3/int, imgt:ndarray/3/int, img1:ndarray/3/int, flow:ndarray/3/float, p:float/0/float · returned tuple · level recorded 2026-09-24
read in 34 papers utils.py ran MIT (permissive) · bbbedcca6e1544a7 · report fixture: signature file:str/0/str · returned ndarray · level recorded 2026-09-24
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
models/IFRNet.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 3073f3b71dc41f8a · report fixture: signature x:Tensor/4/float, scale_factor:float/0/float · returned Tensor · level recorded 2026-09-22
pilot7747/sldl community (archive-listed) 10 samples, 7 ran (3 instrument-failed) · 3 unverified
Decoder1 sldl/video/ifrnet.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 77b300d6590456e1 · report fixture: returned Decoder1 · level recorded 2026-09-22
Decoder4 sldl/video/ifrnet.py ran Apache-2.0 (permissive) · b29aa07553e77b81 · report fixture: signature f0:Tensor/4/float, f1:Tensor/4/float, embt:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Encoder in 278 papers sldl/video/ifrnet.py ran fingerprinted Apache-2.0 (permissive) · 4176171c340a2380 · report fixture: signature img:Tensor/4/float · returned tuple · level recorded 2026-09-24
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
sldl/video/ifrnet.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · a4a1cc910d0e13df · report fixture: returned ResBlock · level recorded 2026-09-22
convrelu in 12 papers sldl/video/ifrnet.py ran · our draft was wrong Apache-2.0 (permissive) · 1a30c25d56937bad · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, groups:int/0/int, bias:bool/0/bool · returned Sequential · level recorded 2026-09-22
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
sldl/video/ifrnet.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 5b17e544cf23ff18 · report fixture: signature x:Tensor/4/float, scale_factor:float/0/float · returned Tensor · level recorded 2026-09-22
warp in 27 papers sldl/video/ifrnet.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · a4d5c37ca03cf29f · report fixture: signature img:Tensor/4/float, flow:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Decoder2 sldl/video/ifrnet.py unverified Apache-2.0 (permissive) · 9d92261879f6a644 · report
Decoder3 sldl/video/ifrnet.py unverified Apache-2.0 (permissive) · 311153678094963f · report
IFRNet sldl/video/ifrnet.py unverified Apache-2.0 (permissive) · b4b68124cf219559 · 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 IFRNet (graph method: IFRNet). 10 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. IFRNet entry · level 0 · unverified · b4b68124cf219559
  2. Decoder1 model · level 1 · ran · 77b300d6590456e1
  3. Decoder2 model · level 0 · unverified · 9d92261879f6a644
  4. Decoder3 model · level 0 · unverified · 311153678094963f
  5. Decoder4 model · level 1 · ran · b29aa07553e77b81
  6. Encoder model · level 1 · ran · 4176171c340a2380
  7. resize helper · level 1 · ran; the contract check could not run (RAISES) · 5b17e544cf23ff18
  8. warp helper · level 1 · ran; the contract check could not run (RAISES) · a4d5c37ca03cf29f
  9. ResBlock model · level 1 · ran · a4a1cc910d0e13df
  10. convrelu helper · level 1 · ran · our draft was wrong · 1a30c25d56937bad

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="2205.14620") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderOptical Flow EstimationVideo Frame Interpolation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_large LPIPS 0.037 #11 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_large MS-SSIM 0.943 #11 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_large PSNR 28.04 #11 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_large SSIM 0.921 #11 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_large VMAF 66.98 #11 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_base LPIPS 0.048 #15 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_base MS-SSIM 0.932 #15 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_base PSNR 27.67 #15 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_base SSIM 0.909 #15 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_base VMAF 64.16 #15 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_small LPIPS 0.049 #16 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_small MS-SSIM 0.931 #16 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_small PSNR 27.45 #16 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_small SSIM 0.908 #16 of 24 Archive leaderboard report
Video Frame Interpolation MSU Video Frame Interpolation IFRNet_small VMAF 63.43 #16 of 24 Archive leaderboard report
Video Frame Interpolation Middlebury IFRNet Interpolation Error 4.216 #1 of 11 Archive leaderboard report
Video Frame Interpolation UCF101 IFRNet PSNR 35.42 #6 of 19 Archive leaderboard report
Video Frame Interpolation UCF101 IFRNet SSIM 0.9698 #6 of 19 Archive leaderboard report
Video Frame Interpolation Vimeo90K IFRNet PSNR 36.20 #5 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K IFRNet SSIM 0.9808 #5 of 23 Archive leaderboard report
Video Frame Interpolation Vimeo90K IFRNet Speed (ms/f) 16 (Tesla V100) #5 of 23 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

SPEED

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