Papers › Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models

Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models

2 Apr 2023CVPR 2023 1arXiv:2304.00600archive 2025-07-28

Paul Micaelli, Arash Vahdat, Hongxu Yin, Jan Kautz, Pavlo Molchanov

Cascaded computation, whereby predictions are recurrently refined over several stages, has been a persistent theme throughout the development of landmark detection models. In this work, we show that the recently proposed Deep Equilibrium Model (DEQ) can be naturally adapted to this form of computation. Our Landmark DEQ (LDEQ) achieves state-of-the-art performance on the challenging WFLW facial landmark dataset, reaching 3.92 NME with fewer parameters and a training memory cost of 𝒪(1) in the number of recurrent modules. Furthermore, we show that DEQs are particularly suited for landmark detection in videos. In this setting, it is typical to train on still images due to the lack of labelled videos. This can lead to a ``flickering'' effect at inference time on video, whereby a model can rapidly oscillate between different plausible solutions across consecutive frames. By rephrasing DEQs as a constrained optimization, we emulate recurrence at inference time, despite not having access to temporal data at training time. This Recurrence without Recurrence (RwR) paradigm helps in reducing landmark flicker, which we demonstrate by introducing a new metric, normalized mean flicker (NMF), and contributing a new facial landmark video dataset (WFLW-V) targeting landmark uncertainty. On the WFLW-V hard subset made up of 500 videos, our LDEQ with RwR improves the NME and NMF by 10 and 13% respectively, compared to the strongest previously published model using a hand-tuned conventional filter.

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 10 code samples harvested from 1 repository linked to this paper: 6 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; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 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, 6 ran (1 with no instrument failure; 5 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

polo5/ldeq_rwr officialmentioned in paperpytorchNOASSERTIONSyntology: 10 samples, 6 ran (5 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

10 samples harvested: 6 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; 5 where Syntology's instrument failed) · 4 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 · our draft was wrong
4ran; the contract check could not run
1ran
4unverified

Licence: 10 of the 10 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 polo5/ldeq_rwr. “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.

polo5/ldeq_rwr official repository 10 samples, 6 ran (5 instrument-failed) · 4 unverified
Conv in 30 papers
census: 8 implementations from 8 papers, 8 distinct outputs across 2 buckets, one shared input per bucket
models/ldeq.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 2531546d22bd2b81 · report fixture: returned Conv · level recorded 2026-09-22
anderson in 7 papers models/ldeq.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence not identified · pointer only · 8a42e2d3d85b6e86 · report fixture: signature f:callable/0/?, x0:Tensor/3/float, m:int/0/int, lam:float/0/float, max_iters:int/0/int, eps:float/0/float, stop_mode:str/0/str, beta:float/0/float, verbose:bool/0/bool, save_trajectory:bool/0/bool · returned dict · level recorded 2026-09-22
broyden in 8 papers models/ldeq.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence not identified · pointer only · c41a2314e7abcf2d · report fixture: signature f:callable/0/?, x0:Tensor/3/float, max_iters:int/0/int, eps:float/0/float, stop_mode:str/0/str, ls:bool/0/bool, verbose:bool/0/bool, save_trajectory:bool/0/bool · returned dict · level recorded 2026-09-22
fpi models/ldeq.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence not identified · pointer only · e7e067191fb77482 · report fixture: signature f:callable/0/?, x0:Tensor/2/float, max_iters:int/0/int, eps:float/0/float, stop_mode:str/0/str, verbose:bool/0/bool, save_trajectory:bool/0/bool · returned tuple · level recorded 2026-09-22
line_search in 14 papers models/ldeq.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence not identified · pointer only · f90371a4652d3eba · report fixture: signature update:Tensor/1/float, x0:Tensor/1/float, g0:Tensor/1/float, g:callable/0/?, on:bool/0/bool · returned tuple · level recorded 2026-09-22
scalar_search_armijo in 11 papers models/ldeq.py ran · our draft was wrong licence not identified · pointer only · 2399ebbc057766ed · report fixture: signature phi:callable/0/?, phi0:Tensor/0/float, derphi0:Tensor/0/float, c1:float/0/float, alpha0:float/0/float, amin:float/0/float · returned tuple · level recorded 2026-09-22
DEQLayer models/ldeq.py unverified licence not identified · pointer only · 8d6ff6218372b364 · report
LDEQ models/ldeq.py unverified licence not identified · pointer only · d6f5cd080de7607b · report
make_cell models/ldeq.py unverified licence not identified · pointer only · 1cf57b33efb6283e · report
root_solver models/ldeq.py unverified licence not identified · pointer only · 07dac41ea941dc90 · 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 Landmark DEQ (LDEQ) (graph method: Landmark DEQ (LDEQ)). 13 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. LDEQ entry · level 0 · unverified · d6f5cd080de7607b
  2. Conv model · level 1 · ran · 2531546d22bd2b81
  3. DEQLayer model · level 0 · unverified · 8d6ff6218372b364
  4. make_cell helper · level 0 · unverified · 1cf57b33efb6283e
  5. root_solver helper · level 0 · unverified · 07dac41ea941dc90
  6. anderson helper · level 1 · ran; the contract check could not run (RAISES) · 8a42e2d3d85b6e86
  7. broyden helper · level 1 · ran; the contract check could not run (RAISES) · c41a2314e7abcf2d
  8. fpi helper · level 1 · ran; the contract check could not run (RAISES) · e7e067191fb77482
  9. line_search helper · level 1 · ran; the contract check could not run (RAISES) · f90371a4652d3eba
  10. matvec helper · level 1 · ran; the contract check could not run · ad49d989d6e115a5
  11. rmatvec helper · level 1 · ran · our draft was wrong · 968a8f446ad3c5b1
  12. _safe_norm helper · level 1 · ran · honoured contract · e2b1ac18e859c77f
  13. scalar_search_armijo helper · level 1 · ran · our draft was wrong · 2399ebbc057766ed

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="2304.00600") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Face Alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Alignment WFLW LDEQ AUC@10 (inter-ocular) 62.4 #2 of 36 Archive leaderboard report
Face Alignment WFLW LDEQ FR@10 (inter-ocular) 2.48 #2 of 36 Archive leaderboard report
Face Alignment WFLW LDEQ NME (inter-ocular) 3.92 #2 of 36 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

DEQ

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