Papers › Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

13 Sep 2021ICCV 2021 10arXiv:2109.05885archive 2025-07-28

Size Wu, Sheng Jin, Wentao Liu, Lei Bai, Chen Qian, Dong Liu, Wanli Ouyang

This paper studies the task of estimating the 3D human poses of multiple persons from multiple calibrated camera views. Following the top-down paradigm, we decompose the task into two stages, i.e. person localization and pose estimation. Both stages are processed in coarse-to-fine manners. And we propose three task-specific graph neural networks for effective message passing. For 3D person localization, we first use Multi-view Matching Graph Module (MMG) to learn the cross-view association and recover coarse human proposals. The Center Refinement Graph Module (CRG) further refines the results via flexible point-based prediction. For 3D pose estimation, the Pose Regression Graph Module (PRG) learns both the multi-view geometry and structural relations between human joints. Our approach achieves state-of-the-art performance on CMU Panoptic and Shelf datasets with significantly lower computation complexity.

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

The archive's official repository (wusize/multiview_pose) was not harvested; the 22 samples below come from 1 repository the archive does not mark official.

Syntology 22 code samples harvested from 1 repository linked to this paper: 19 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 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: found in paper text by Syntology: 22 samples from 1 repository, 19 ran (12 with no instrument failure; 7 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.

wusize/multiview_pose officialmentioned on GitHubpytorchSyntology: 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.

Code Syntology ran Syntology

22 samples harvested: 19 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 7 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 · violated contract
5ran · our draft was wrong
2ran; the contract check could not run
11ran
3unverified

Licence: 0 of the 22 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 microsoft/voxelpose-pytorch. “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 2 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.

microsoft/voxelpose-pytorch found in paper text by Syntology 22 samples, 19 ran (7 instrument-failed) · 3 unverified
Basic3DBlock lib/models/multi_person_posenet.py ran MIT (permissive) · e879f43ac29c8209 · report fixture: returned Basic3DBlock · level recorded 2026-09-22
EncoderDecorder lib/models/multi_person_posenet.py ran MIT (permissive) · e8bb60b582c2affd · report fixture: returned EncoderDecorder · level recorded 2026-09-22
PerJointL1Loss lib/models/multi_person_posenet.py ran fingerprinted MIT (permissive) · 6107a2be532d1330 · report fixture: signature output:Tensor/3/float, target:Tensor/3/float, use_target_weight:bool/0/bool, target_weight:Tensor/3/float · returned Tensor · level recorded 2026-09-24
PerJointMSELoss lib/models/multi_person_posenet.py ran fingerprinted MIT (permissive) · 9d1c5d2a5a6c24e6 · report fixture: signature output:Tensor/4/float, target:Tensor/4/float, use_target_weight:bool/0/bool, target_weight:NoneType/0/? · returned Tensor · level recorded 2026-09-24
Pool3DBlock lib/models/multi_person_posenet.py ran fingerprinted MIT (permissive) · ec6cfed3d98141ca · report fixture: returned Pool3DBlock · level recorded 2026-09-22
ProjectLayer lib/models/multi_person_posenet.py ran MIT (permissive) · 744d63366179beb0 · report fixture: returned ProjectLayer · level recorded 2026-09-22
ProposalLayer lib/models/multi_person_posenet.py ran fingerprinted MIT (permissive) · 68e1c779a38301ad · report fixture: returned ProposalLayer · level recorded 2026-09-22
Res3DBlock lib/models/multi_person_posenet.py ran MIT (permissive) · 582e26415bfd114c · report fixture: returned Res3DBlock · level recorded 2026-09-22
SoftArgmaxLayer lib/models/multi_person_posenet.py ran MIT (permissive) · dc41bb35432b99fb · report fixture: signature x:Tensor/4/float, grids:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Upsample3DBlock lib/models/multi_person_posenet.py ran MIT (permissive) · 56a3fdc52ef86408 · report fixture: returned Upsample3DBlock · level recorded 2026-09-22
V2VNet lib/models/multi_person_posenet.py ran MIT (permissive) · a27e057355474941 · report fixture: returned V2VNet · level recorded 2026-09-22
get_3rd_point in 8 papers lib/models/multi_person_posenet.py ran; the contract check could not run (RAISES) MIT (permissive) · 1adda80cee295b0e · report fixture: signature a:ndarray/1/float, b:ndarray/1/float · returned ndarray · level recorded 2026-09-22
get_dir in 14 papers lib/models/multi_person_posenet.py ran · violated contract fingerprinted MIT (permissive) · 5d546e1ecbee1866 · report fixture: signature src_point:list/1/float, rot_rad:float/0/float · returned list · level recorded 2026-09-22
get_index in 27 papers lib/models/multi_person_posenet.py ran · our draft was wrong fingerprinted MIT (permissive) · 346171f4d8f86b44 · report fixture: signature indices:Tensor/3/int, shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
max_pool in 11 papers lib/models/multi_person_posenet.py ran · our draft was wrong fingerprinted MIT (permissive) · 6c9fb0f42d59408f · report fixture: signature inputs:Tensor/5/float, kernel:int/0/int · returned Tensor · level recorded 2026-09-22
nms in 65 papers lib/models/multi_person_posenet.py ran · our draft was wrong fingerprinted MIT (permissive) · 09efa3ac3e5d405e · report fixture: signature root_cubes:Tensor/5/float, max_num:int/0/int · returned tuple · level recorded 2026-09-22
project_point_radial lib/models/multi_person_posenet.py ran · our draft was wrong fingerprinted MIT (permissive) · b2016bca44e2e224 · report fixture: signature x:Tensor/2/float, R:Tensor/2/float, T:Tensor/2/float, f:Tensor/0/float, c:Tensor/2/float, k:Tensor/2/float, p:Tensor/2/float · returned Tensor · level recorded 2026-09-22
project_pose lib/models/multi_person_posenet.py ran; the contract check could not run (RAISES) MIT (permissive) · 6b380ea1a8788e2f · report fixture: signature x:Tensor/2/float, camera:dict/0/? · returned Tensor · level recorded 2026-09-22
unfold_camera_param lib/models/multi_person_posenet.py ran · our draft was wrong MIT (permissive) · ad30051ce03d273d · report fixture: signature camera:dict/0/?, device:NoneType/0/? · returned tuple · level recorded 2026-09-22
CuboidProposalNet lib/models/multi_person_posenet.py unverified MIT (permissive) · 238c684df17d3359 · report
MultiPersonPoseNet lib/models/multi_person_posenet.py unverified MIT (permissive) · b5635deb75d47f46 · report
PoseRegressionNet lib/models/multi_person_posenet.py unverified MIT (permissive) · c3f2cff95d086457 · 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 Multi-view Matching Graph Module (MMG) (graph method: Multi-view Matching Graph Module (MMG)). 22 bricks; individually on a fixture: 19 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. MultiPersonPoseNet entry · level 0 · unverified · b5635deb75d47f46
  2. CuboidProposalNet model · level 0 · unverified · 238c684df17d3359
  3. PerJointL1Loss helper · level 1 · ran · 6107a2be532d1330
  4. PerJointMSELoss helper · level 1 · ran · 9d1c5d2a5a6c24e6
  5. PoseRegressionNet model · level 0 · unverified · c3f2cff95d086457
  6. ProjectLayer helper · level 1 · ran · 744d63366179beb0
  7. ProposalLayer model · level 1 · ran · 68e1c779a38301ad
  8. V2VNet helper · level 1 · ran · a27e057355474941
  9. SoftArgmaxLayer model · level 1 · ran · dc41bb35432b99fb
  10. project_pose helper · level 1 · ran; the contract check could not run (RAISES) · 6b380ea1a8788e2f
  11. nms helper · level 1 · ran · our draft was wrong · 09efa3ac3e5d405e
  12. Basic3DBlock helper · level 1 · ran · e879f43ac29c8209
  13. EncoderDecorder helper · level 1 · ran · e8bb60b582c2affd
  14. Res3DBlock helper · level 1 · ran · 582e26415bfd114c
  15. project_point_radial helper · level 1 · ran · our draft was wrong · b2016bca44e2e224
  16. unfold_camera_param helper · level 1 · ran · our draft was wrong · ad30051ce03d273d
  17. get_index helper · level 1 · ran · our draft was wrong · 346171f4d8f86b44
  18. max_pool helper · level 1 · ran · our draft was wrong · 6c9fb0f42d59408f
  19. Pool3DBlock helper · level 1 · ran · ec6cfed3d98141ca
  20. Upsample3DBlock helper · level 1 · ran · 56a3fdc52ef86408
  21. get_3rd_point helper · level 1 · ran; the contract check could not run (RAISES) · 1adda80cee295b0e
  22. get_dir helper · level 1 · ran · violated contract · 5d546e1ecbee1866

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="2109.05885") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Multi-Person Pose Estimation3D Pose EstimationMulti-Person Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Multi-Person Pose Estimation Panoptic PRGN Average MPJPE (mm) 15.68 #2 of 20 Archive leaderboard report
3D Multi-Person Pose Estimation Shelf PRGN PCP3D 97.7 #7 of 27 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