Papers › Segmenting Moving Objects via an Object-Centric Layered Representation

Segmenting Moving Objects via an Object-Centric Layered Representation

5 Jul 2022arXiv:2207.02206archive 2025-07-28

Junyu Xie, Weidi Xie, Andrew Zisserman

The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video. We make four contributions: First, we introduce an object-centric segmentation model with a depth-ordered layer representation. This is implemented using a variant of the transformer architecture that ingests optical flow, where each query vector specifies an object and its layer for the entire video. The model can effectively discover multiple moving objects and handle mutual occlusions; Second, we introduce a scalable pipeline for generating multi-object synthetic training data via layer compositions, that is used to train the proposed model, significantly reducing the requirements for labour-intensive annotations, and supporting Sim2Real generalisation; Third, we conduct thorough ablation studies, showing that the model is able to learn object permanence and temporal shape consistency, and is able to predict amodal segmentation masks; Fourth, we evaluate our model, trained only on synthetic data, on standard video segmentation benchmarks, DAVIS, MoCA, SegTrack, FBMS-59, and achieve state-of-the-art performance among existing methods that do not rely on any manual annotations. With test-time adaptation, we observe further performance boosts.

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 21 code samples harvested from 1 repository linked to this paper: 16 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 16 ran (12 with no instrument failure; 4 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.

Jyxarthur/OCLR_model officialmentioned on GitHubpytorchSyntology: 21 samples, 16 ran (4 instrument-failed) · 5 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

21 samples harvested: 16 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 5 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
4ran · our draft was wrong
11ran
5unverified

Licence: 0 of the 21 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 Jyxarthur/OCLR_model. “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 4 samples 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.

Jyxarthur/OCLR_model official repository 21 samples, 16 ran (4 instrument-failed) · 5 unverified
AttnMap models/oclr.py ran MIT (permissive) · 867da52dc8c76b0f · report fixture: returned AttnMap · level recorded 2026-09-22
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/oclr.py ran fingerprinted MIT (permissive) · 75d889c61752310c · report fixture: returned ConvBlock · level recorded 2026-09-22
EncoderLayer in 73 papers models/oclr.py ran MIT (permissive) · 8378236c795fdc48 · report fixture: returned EncoderLayer · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
models/oclr.py ran fingerprinted MIT (permissive) · a447981fffd42b39 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
Norm in 13 papers models/oclr.py ran MIT (permissive) · 55e3d071afe4d46b · report fixture: returned Norm · level recorded 2026-09-22
OrderingHead models/oclr.py ran MIT (permissive) · f66e673c9146f36d · report fixture: returned OrderingHead · level recorded 2026-09-22
SoftPositionTimeEmbed models/oclr.py ran MIT (permissive) · 47038bfa9f36a207 · report fixture: returned SoftPositionTimeEmbed · level recorded 2026-09-22
SoftTimeEmbed models/oclr.py ran MIT (permissive) · fcbab3ccaf3b573d · report fixture: returned SoftTimeEmbed · level recorded 2026-09-22
TransDecoder models/oclr.py ran MIT (permissive) · d4e6b98e360c24bf · report fixture: signature x:Tensor/3/float, e_outputs:Tensor/3/float, src_mask:Tensor/3/float, trg_mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
UNet_decoder models/oclr.py ran MIT (permissive) · 1c0dce82d6701d1a · report fixture: returned UNet_decoder · level recorded 2026-09-22
UNet_encoder models/oclr.py ran MIT (permissive) · 5a52ccb38fd0d98e · report fixture: returned UNet_encoder · level recorded 2026-09-22
_in_projection_packed models/oclr.py ran · our draft was wrong fingerprinted MIT (permissive) · a6a5c2077b398c5d · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, w:Tensor/2/float, b:Tensor/1/float · returned tuple · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 4 of 5, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 4, kind float, dtype float32 · arg 3: rank 4, kind float, dtype float32 · arg 4: rank 4, kind int, dtype int64
models/oclr.py ran · our draft was wrong MIT (permissive) · 86341ad6b5c2c7a4 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float, d_k:int/0/int, mask:Tensor/4/int, dropout:callable/0/? · returned Tensor · level recorded 2026-09-22
attn_mask models/oclr.py ran · our draft was wrong MIT (permissive) · 6cb4b60cb90aeb1d · report fixture: signature frames:int/0/int, resolution:tuple/1/int · returned Tensor · level recorded 2026-09-22
build_spacetime_grid models/oclr.py ran · our draft was wrong MIT (permissive) · 584cc60931efa04b · report fixture: signature frames:int/0/int, resolution:list/1/int · returned Tensor · level recorded 2026-09-22
build_time_grid models/oclr.py ran · honoured contract MIT (permissive) · 7a79f5c1eb6acc1b · report fixture: signature frames:int/0/int · returned Tensor · level recorded 2026-09-22
BTNTransformerDec models/oclr.py unverified MIT (permissive) · 34a9dcdc4c7bfe30 · report
BTNTransformerEnc models/oclr.py unverified MIT (permissive) · 2d11b5a36034202a · report
DecoderLayer in 43 papers models/oclr.py unverified MIT (permissive) · 137850413fc262a6 · report
OCLR models/oclr.py unverified MIT (permissive) · 09bb9b075e9f690d · report
TransEncoder models/oclr.py unverified MIT (permissive) · 1eceb7d7a75f267f · 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 object-centric segmentation model with a depth-ordered layer representation (graph method: object-centric segmentation model with a depth-ordered layer representation). 22 bricks; individually on a fixture: 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. OCLR entry · level 0 · unverified · 09bb9b075e9f690d
  2. AttnMap model · level 1 · ran · 867da52dc8c76b0f
  3. BTNTransformerDec model · level 0 · unverified · 34a9dcdc4c7bfe30
  4. BTNTransformerEnc model · level 0 · unverified · 2d11b5a36034202a
  5. OrderingHead model · level 1 · ran · f66e673c9146f36d
  6. UNet_decoder helper · level 1 · ran · 1c0dce82d6701d1a
  7. UNet_encoder model · level 1 · ran · 5a52ccb38fd0d98e
  8. SoftTimeEmbed helper · level 1 · ran · fcbab3ccaf3b573d
  9. TransDecoder model · level 1 · ran · d4e6b98e360c24bf
  10. SoftPositionTimeEmbed helper · level 1 · ran · 47038bfa9f36a207
  11. TransEncoder model · level 0 · unverified · 1eceb7d7a75f267f
  12. attn_mask helper · level 1 · ran · our draft was wrong · 6cb4b60cb90aeb1d
  13. ConvBlock helper · level 1 · ran · 75d889c61752310c
  14. build_time_grid helper · level 1 · ran · honoured contract · 7a79f5c1eb6acc1b
  15. DecoderLayer helper · level 0 · unverified · 137850413fc262a6
  16. get_clones helper · level 1 · ran · our draft was wrong · 891b8ebab395921f
  17. build_spacetime_grid helper · level 1 · ran · our draft was wrong · 584cc60931efa04b
  18. EncoderLayer helper · level 1 · ran · 8378236c795fdc48
  19. MultiHeadAttention model · level 1 · ran · a447981fffd42b39
  20. Norm helper · level 1 · ran · 55e3d071afe4d46b
  21. _in_projection_packed helper · level 1 · ran · our draft was wrong · a6a5c2077b398c5d
  22. attention helper · level 1 · ran · our draft was wrong · 86341ad6b5c2c7a4

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="2207.02206") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Instance SegmentationMotion SegmentationObjectSegmentationTest-time AdaptationUnsupervised Object SegmentationVideo Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Object Segmentation DAVIS 2016 OCLR J score 72.1 #4 of 9 Archive leaderboard report
Unsupervised Object Segmentation FBMS-59 OCLR mIoU 65.4 #3 of 7 Archive leaderboard report
Unsupervised Object Segmentation SegTrack-v2 OCLR mIoU 67.6 #3 of 8 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