Papers › What Matters in Unsupervised Optical Flow

What Matters in Unsupervised Optical Flow

8 Jun 2020ECCV 2020 8arXiv:2006.04902archive 2025-07-28

Rico Jonschkowski, Austin Stone, Jonathan T. Barron, Ariel Gordon, Kurt Konolige, Anelia Angelova

We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a number of novel improvements to unsupervised flow models, such as cost volume normalization, stopping the gradient at the occlusion mask, encouraging smoothness before upsampling the flow field, and continual self-supervision with image resizing. By combining the results of our investigation with our improved model components, we are able to present a new unsupervised flow technique that significantly outperforms the previous unsupervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches.

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

No sample from the archive's official repository (google-research/google-research) is linked to this paper; the 17 samples below come from 1 community repository. Syntology harvested code from google-research/google-research for 24 other papers.

google-research/google-research: Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 17 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 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): 17 samples from 1 repository, 16 ran (16 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 1 of its repositories that Syntology harvested for other papers:

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/google-research officialtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 1 ran (of which 1 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
junbongjang/contour-tracking mentioned on GitHubtfApache-2.0Syntology: 17 samples, 16 ran (0 instrument-failed) · 1 unverified report
2023-MindSpore-1/ms-code-36 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code3 mindsporeSyntology: not harvested report
cfreshgirl/uflow mindsporeSyntology: not harvested 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

17 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 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
15ran
1unverified

Licence: 1 of the 17 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 junbongjang/contour-tracking. “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.

junbongjang/contour-tracking community (archive-listed) 17 samples, 16 ran (0 instrument-failed) · 1 unverified
compute_cost_volume src/contour_flow_model.py ran Apache-2.0 (permissive) · f1a6a5a446ff10ba · report fixture: signature features1:EagerTensor/4/float, features2:EagerTensor/4/float, max_displacement:int/0/int · returned EagerTensor · level recorded 2026-09-24
corr_2d_loss src/tracking_utils.py ran Apache-2.0 (permissive) · e3a04fdb34e68bb4 · report fixture: signature gt_prev_id_assignments:EagerTensor/3/int, gt_cur_id_assignments:EagerTensor/3/int, corr_2d_matrix:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
get_closest_indices_from_gt_and_pred src/preprocessing/contour_tracking_manuscript_figures.py ran Apache-2.0 (permissive) · bc7e65890c171b15 · report fixture: signature init_gt_points:ndarray/2/float, pred_points:ndarray/2/float · returned list · level recorded 2026-09-24
get_image_name in 5 papers src/preprocessing/MATLAB_tracking_points.py ran fingerprinted Apache-2.0 (permissive) · 70452baab57f53ae · report fixture: signature image_path:str/0/str, image_format:str/0/str · returned str · level recorded 2026-09-24
get_ordered_contour_points_from_mask src/preprocessing/main_process_tracking_points.py ran Apache-2.0 (permissive) · 89b3af1de1b9d022 · report fixture: signature a_mask:ndarray/2/int · returned ndarray · level recorded 2026-09-24
move_prev_tracked_point_and_align_to_smoothEdge src/preprocessing/MATLAB_tracking_points.py ran Apache-2.0 (permissive) · c6232c156aca7856 · report fixture: signature cur_smoothedEdge:ndarray/2/float, next_smoothedEdge:ndarray/2/float, cur_protrusion:ndarray/2/float, cur_smoothedEdge_index:int/0/int · returned int · level recorded 2026-09-24
normalize_features in 20 papers src/contour_flow_model.py ran Apache-2.0 (permissive) · d0f7630cddfa3a3a · report fixture: signature feature_list:list/1/EagerTensor, normalize:bool/0/bool, center:bool/0/bool, moments_across_channels:bool/0/bool, moments_across_images:bool/0/bool · returned list · level recorded 2026-09-24
normalize_points src/metrics.py ran fingerprinted Apache-2.0 (permissive) · d654e53ca581da7f · report fixture: signature pts:ndarray/2/float, image_width:int/0/int, image_height:int/0/int · returned ndarray · level recorded 2026-09-24
point_wise_spatial_accuracy src/metrics.py ran Apache-2.0 (permissive) · 5a5cd48d24333dfe · report fixture: signature ps1:ndarray/2/float, ps2:ndarray/2/float, image_width:int/0/int, image_height:int/0/int, thresh:float/0/float · returned ndarray · level recorded 2026-09-24
prevent_trajectory_cross src/preprocessing/contour_tracking_manuscript_figures.py ran fingerprinted Apache-2.0 (permissive) · 5e16d4d82c56238b · report fixture: signature pred_tracking_points_contour_indices:ndarray/1/int · returned ndarray · level recorded 2026-09-24
remove_points_touching_image_boundary src/preprocessing/main_process_tracking_points.py ran Apache-2.0 (permissive) · 4c9c5b3ef68583d8 · report fixture: signature ordered_contour_points:ndarray/2/int, a_image:ndarray/2/int · returned ndarray · level recorded 2026-09-24
reorder_contour_points src/preprocessing/main_process_tracking_points.py ran fingerprinted Apache-2.0 (permissive) · a92d51e83bd4b792 · report fixture: signature processed_ordered_contour_points:ndarray/2/float, height:int/0/int, width:int/0/int · returned ndarray · level recorded 2026-09-24
robust_l1 src/tracking_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 94e47e87bb26b846 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
robust_l2 src/tracking_utils.py ran fingerprinted Apache-2.0 (permissive) · 8f9b339cc1ef3aa1 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
sample_few_tracking_points src/preprocessing/MATLAB_tracking_points.py ran fingerprinted Apache-2.0 (permissive) · 6db48046c588fa46 · report fixture: signature contour_points:ndarray/2/float, NUM_SAMPLE_POINTS:int/0/int · returned ndarray · level recorded 2026-09-24
spatial_accuracy src/metrics.py ran Apache-2.0 (permissive) · bd7b2699ab4e54af · report fixture: signature ps1:ndarray/2/float, ps2:ndarray/2/float, image_width:int/0/int, image_height:int/0/int, thresh:float/0/float · returned float64 · level recorded 2026-09-24
check_model_frozen src/contour_flow_main.py unverified Apache-2.0 (permissive) · 36e04cd3ded65746 · report

Tasks

Occlusion HandlingOptical Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation Sintel Clean unsupervised UFlow Average End-Point Error 5.21 #5 of 5 Archive leaderboard report
Optical Flow Estimation Sintel Final unsupervised UFlow Average End-Point Error 6.50 #5 of 5 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