Papers › FlowNet: Learning Optical Flow with Convolutional Networks

FlowNet: Learning Optical Flow with Convolutional Networks

26 Apr 2015ICCV 2015 12arXiv:1504.06852archive 2025-07-28

Philipp Fischer, Alexey Dosovitskiy, Eddy Ilg, Philip Häusser, Caner Hazırbaş, Vladimir Golkov, Patrick van der Smagt, Daniel Cremers, Thomas Brox

Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks where CNNs were successful. In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations. Since existing ground truth data sets are not sufficiently large to train a CNN, we generate a synthetic Flying Chairs dataset. We show that networks trained on this unrealistic data still generalize very well to existing datasets such as Sintel and KITTI, achieving competitive accuracy at frame rates of 5 to 10 fps.

PaperPDFConference PDFCodeCode 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 20 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 20 samples from 3 repositories, 13 ran (13 with no instrument failure; 0 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.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

18 repositories listed; official and paper-mentioned ones first.

ClementPinard/Pytorch-Correlation-extension mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
McDo/LightFlowPytorch mentioned on GitHubpytorchMITSyntology: 17 samples, 12 ran (0 instrument-failed) · 5 unverified report
a-doering/tracker_w_correlation_motion_model mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tracking without bells and whistles (arXiv:1903.05625; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ankitAMD/Optical-Flow_Python mentioned on GitHubSyntology: not harvested report
guanfuchen/video_obj mentioned on GitHubpytorchSyntology: not harvested report
jgorgenucsd/corr_tf mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
lab-midas/lapnet mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks (arXiv:1612.01925; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
msracver/Deep-Feature-Flow mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Feature Flow for Video Recognition (arXiv:1611.07715; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
neu-vi/ezflow mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation (arXiv:2010.14851; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
neu-vig/ezflow mentioned on GitHubpytorchMITSyntology: not harvested report
philferriere/tfoptflow mentioned on GitHubtfSyntology: not harvested report
remibasaru/Flow-Net mentioned on GitHubtfSyntology: not harvested report
rickyHong/tfoptflow-repl mentioned on GitHubtfSyntology: not harvested report
simonmeister/UnFlow mentioned on GitHubtfSyntology: not harvested report
yukitsuji/chainer_function mentioned on GitHubSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
ClementPinard/FlowNetPytorch pytorchSyntology: 2 samples, 0 ran · 2 unverified report
open-mmlab/mmflow pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Estimate Hidden Motions with Global Motion Aggregation (arXiv:2104.02409; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 7 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 · violated contract
12ran
7unverified

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 3 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”. “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.

ClementPinard/Pytorch-Correlation-extension community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_grads in 13 papers check.py ran MIT (permissive) · 19ee68e6a7f1011b · report fixture: signature variables:list/1/Tensor · returned list · level recorded 2026-09-26
McDo/LightFlowPytorch community (archive-listed) 17 samples, 12 ran (0 instrument-failed) · 5 unverified
EPE in 8 papers loss.py ran MIT (permissive) · b77a7cb2a29a19c7 · report fixture: signature input_flow:Tensor/2/float, target_flow:Tensor/2/float, sparse:bool/0/bool, mean:bool/0/bool · returned Tensor · level recorded 2026-09-26
L1Loss in 6 papers loss.py ran fingerprinted MIT (permissive) · e58f02bc54cf9db9 · report fixture: signature output:Tensor/4/float, target:Tensor/4/float, sparse:bool/0/bool · returned Tensor · level recorded 2026-09-26
L2Loss loss.py ran fingerprinted MIT (permissive) · 1869efdefff249d5 · report fixture: signature output:Tensor/4/float, target:Tensor/4/float, sparse:bool/0/bool · returned Tensor · level recorded 2026-09-26
adjust_learning_rate in 125 papers utils/util.py ran MIT (permissive) · 97509470e0c1680e · report fixture: signature args:Args/0/?, optimizer:SGD/0/?, epoch:int/0/int, epoch_size:int/0/int · returned float · level recorded 2026-09-26
compute_color in 11 papers utils/flowlib.py ran fingerprinted MIT (permissive) · ab41dcb0fc2e9217 · report fixture: signature u:ndarray/2/float, v:ndarray/2/float · returned ndarray · level recorded 2026-09-26
conv_dw in 13 papers models/FlowNetL.py ran MIT (permissive) · fd0432127db8b8c0 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-26
flow_to_image in 11 papers utils/flowlib.py ran fingerprinted MIT (permissive) · 11b939d4bfc443d5 · report fixture: signature flow:ndarray/3/float · returned ndarray · level recorded 2026-09-26
make_dataset in 144 papers datasets/KITTI.py ran MIT (permissive) · 97658411b60eb6fa · report fixture: returned list · level recorded 2026-09-26
make_dataset in 144 papers datasets/mpisintel.py ran MIT (permissive) · bd1431a30359f7b7 · report fixture: returned list · level recorded 2026-09-26
read_flow utils/flowlib.py ran MIT (permissive) · 9c84ff434efaba0b · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-26
split2list datasets/util.py ran MIT (permissive) · 1fe407a51fa0b922 · report fixture: signature images:list/1/str, split:float/0/float, default_split:float/0/float · returned tuple · level recorded 2026-09-26
str2bool in 533 papers utils/util.py ran · violated contract MIT (permissive) · 25c7475539e39da4 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
KITTI_loader datasets/KITTI.py unverified MIT (permissive) · 4e7beea709169af7 · report
flownetl models/FlowNetL.py unverified MIT (permissive) · 83d924e4f07e21c6 · report
flying_chairs datasets/flyingchairs.py unverified MIT (permissive) · e851f9b7068b4e4a · report
load_flow_from_png datasets/KITTI.py unverified MIT (permissive) · 8f05b2af27a4b333 · report
make_dataset in 144 papers datasets/flyingchairs.py unverified MIT (permissive) · 5b483f6b2c434ae9 · report
ClementPinard/FlowNetPytorch community (archive-listed) 2 samples, 0 ran · 2 unverified
flownetc models/FlowNetC.py unverified MIT (permissive) · 2e9326c5343dd6d0 · report
flownetc_bn models/FlowNetC.py unverified MIT (permissive) · 59b45a46f776690d · report

Tasks

Optical Flow Estimation

Datasets

Introduced by this paper, per the archive.

FlyingChairs

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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