Papers › Learnable Triangulation of Human Pose

Learnable Triangulation of Human Pose

14 May 2019ICCV 2019 10arXiv:1905.05754archive 2025-07-28

Karim Iskakov, Egor Burkov, Victor Lempitsky, Yury Malkov

We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views. The first (baseline) solution is a basic differentiable algebraic triangulation with an addition of confidence weights estimated from the input images. The second solution is based on a novel method of volumetric aggregation from intermediate 2D backbone feature maps. The aggregated volume is then refined via 3D convolutions that produce final 3D joint heatmaps and allow modelling a human pose prior. Crucially, both approaches are end-to-end differentiable, which allows us to directly optimize the target metric. We demonstrate transferability of the solutions across datasets and considerably improve the multi-view state of the art on the Human3.6M dataset. Video demonstration, annotations and additional materials will be posted on our project page (https://saic-violet.github.io/learnable-triangulation).

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="1905.05754")

Code

Syntology Ran 1 of 17 code samples harvested from 1 repository linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 17 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

karfly/learnable-triangulation-pytorch mentioned 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

17 samples harvested; 1 ran; 0 honoured the contract we drafted; 16 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.

1ran · our draft was wrong
16unverified

Licence: 0 of the 17 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 karfly/learnable-triangulation-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. “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.

conv3x3 karfly/learnable-triangulation-pytorch/mvn/models/pose_resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
calc_gradient_norm karfly/learnable-triangulation-pytorch/mvn/utils/misc.py community (archive-listed) unverified MIT (permissive) · c37b9335c3c1e219 · report
config_to_str karfly/learnable-triangulation-pytorch/mvn/utils/misc.py community (archive-listed) unverified MIT (permissive) · 9e08201135438284 · report
crop_image karfly/learnable-triangulation-pytorch/mvn/utils/img.py community (archive-listed) unverified MIT (permissive) · 97259a9e1f81bfef · report
euclidean_to_homogeneous karfly/learnable-triangulation-pytorch/mvn/utils/multiview.py community (archive-listed) unverified MIT (permissive) · 41a9f998b3e64792 · report
fig_to_array karfly/learnable-triangulation-pytorch/mvn/utils/vis.py community (archive-listed) unverified MIT (permissive) · 92ebb319daf6e5c7 · report
get_pose_net karfly/learnable-triangulation-pytorch/mvn/models/pose_resnet.py community (archive-listed) unverified MIT (permissive) · 4b5bb331e9336255 · report
get_rotation_matrix karfly/learnable-triangulation-pytorch/mvn/utils/volumetric.py community (archive-listed) unverified MIT (permissive) · 3d898c27df7d558a · report
get_square_bbox karfly/learnable-triangulation-pytorch/mvn/utils/img.py community (archive-listed) unverified MIT (permissive) · 058c2ac5b4914ae8 · report
homogeneous_to_euclidean karfly/learnable-triangulation-pytorch/mvn/utils/multiview.py community (archive-listed) unverified MIT (permissive) · f8bdb55803874cd3 · report
integrate_tensor_2d karfly/learnable-triangulation-pytorch/mvn/utils/op.py community (archive-listed) unverified MIT (permissive) · 1746cfe037b9bddc · report
integrate_tensor_3d karfly/learnable-triangulation-pytorch/mvn/utils/op.py community (archive-listed) unverified MIT (permissive) · 3438dea94010a241 · report
integrate_tensor_3d_with_coordinates karfly/learnable-triangulation-pytorch/mvn/utils/op.py community (archive-listed) unverified MIT (permissive) · 200b87aeadd93f7a · report
make_collate_fn karfly/learnable-triangulation-pytorch/mvn/datasets/utils.py community (archive-listed) unverified MIT (permissive) · 401a09672d24d91d · report
project_3d_points_to_image_plane_without_distortion karfly/learnable-triangulation-pytorch/mvn/utils/multiview.py community (archive-listed) unverified MIT (permissive) · 5d25c0684ed04e72 · report
resize_image karfly/learnable-triangulation-pytorch/mvn/utils/img.py community (archive-listed) unverified MIT (permissive) · 3658ef58769f24d4 · report
rotate_coord_volume karfly/learnable-triangulation-pytorch/mvn/utils/volumetric.py community (archive-listed) unverified MIT (permissive) · 621b296fbf0065a0 · report

Tasks

3D Human Pose EstimationMulti-view 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Panoptic Learnable Triangulation of Human Pose Average MPJPE (mm) 13.7 #3 of 9 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