Papers › HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose...

HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation

11 May 2023CVPR 2023 1arXiv:2305.06968archive 2025-07-28

Akash Sengupta, Ignas Budvytis, Roberto Cipolla

Monocular 3D human pose and shape estimation is an ill-posed problem since multiple 3D solutions can explain a 2D image of a subject. Recent approaches predict a probability distribution over plausible 3D pose and shape parameters conditioned on the image. We show that these approaches exhibit a trade-off between three key properties: (i) accuracy - the likelihood of the ground-truth 3D solution under the predicted distribution, (ii) sample-input consistency - the extent to which 3D samples from the predicted distribution match the visible 2D image evidence, and (iii) sample diversity - the range of plausible 3D solutions modelled by the predicted distribution. Our method, HuManiFlow, predicts simultaneously accurate, consistent and diverse distributions. We use the human kinematic tree to factorise full body pose into ancestor-conditioned per-body-part pose distributions in an autoregressive manner. Per-body-part distributions are implemented using normalising flows that respect the manifold structure of SO(3), the Lie group of per-body-part poses. We show that ill-posed, but ubiquitous, 3D point estimate losses reduce sample diversity, and employ only probabilistic training losses. Code is available at: https://github.com/akashsengupta1997/HuManiFlow.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.06968")

Code

Syntology Ran 3 of 6 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 6 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

akashsengupta1997/humaniflow officialmentioned in papermentioned on GitHubpytorchMIT 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

6 samples harvested; 3 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
3unverified

Licence: 0 of the 6 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 akashsengupta1997/humaniflow. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv1x1 akashsengupta1997/humaniflow/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 akashsengupta1997/humaniflow/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
conv3x3 akashsengupta1997/humaniflow/models/pose2D_hrnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_pose_net akashsengupta1997/humaniflow/models/pose2D_hrnet.py official repository unverified MIT (permissive) · 2534c81208f21998 · report
immediate_parent_to_all_ancestors akashsengupta1997/humaniflow/models/humaniflow_model.py official repository unverified MIT (permissive) · b3b1eaa6fe86547f · report
resnet18 akashsengupta1997/humaniflow/models/resnet.py official repository unverified MIT (permissive) · 055a5e7106b48fd2 · report

Tasks

3D Human Pose Estimation3D human pose and shape estimationDiversityMulti-Hypotheses 3D Human Pose EstimationNormalising Flows

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW HuManiFlow MPJPE 83.9 #79 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW HuManiFlow PA-MPJPE 53.4 #79 of 119 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HuManiFlow Best-Hypothesis MPJPE (n = 25) - #10 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HuManiFlow Best-Hypothesis PMPJPE (n = 25) - #10 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HuManiFlow H36M PMPJPE (n = 1) - #10 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HuManiFlow H36M PMPJPE (n = 25) - #10 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M HuManiFlow Most-Likely Hypothesis PMPJPE (n = 1) - #10 of 10 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