Papers › SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

18 Jul 2020ECCV 2020 8arXiv:2007.09389archive 2025-07-28

Ailing Zeng, Xiao Sun, Fuyang Huang, Minhao Liu, Qiang Xu, Stephen Lin

Human poses that are rare or unseen in a training set are challenging for a network to predict. Similar to the long-tailed distribution problem in visual recognition, the small number of examples for such poses limits the ability of networks to model them. Interestingly, local pose distributions suffer less from the long-tail problem, i.e., local joint configurations within a rare pose may appear within other poses in the training set, making them less rare. We propose to take advantage of this fact for better generalization to rare and unseen poses. To be specific, our method splits the body into local regions and processes them in separate network branches, utilizing the property that a joint position depends mainly on the joints within its local body region. Global coherence is maintained by recombining the global context from the rest of the body into each branch as a low-dimensional vector. With the reduced dimensionality of less relevant body areas, the training set distribution within network branches more closely reflects the statistics of local poses instead of global body poses, without sacrificing information important for joint inference. The proposed split-and-recombine approach, called SRNet, can be easily adapted to both single-image and temporal models, and it leads to appreciable improvements in the prediction of rare and unseen poses.

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="2007.09389")

Code

Syntology Ran 1 of 9 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 9 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.

ailingzengzzz/Split-and-Recombine-Net officialmentioned on GitHubpytorchApache-2.0 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

9 samples harvested; 1 ran; 0 honoured the contract we drafted; 8 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
8unverified

Licence: 0 of the 9 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 ailingzengzzz/Split-and-Recombine-Net. “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.

mpjpe ailingzengzzz/Split-and-Recombine-Net/common/common_pytorch/loss/loss_family.py official repository ran fingerprinted Apache-2.0 (permissive) · 3afb541a8147d123 · report
axis_rotation ailingzengzzz/Split-and-Recombine-Net/common/transformation/aug_rotate.py official repository unverified Apache-2.0 (permissive) · be5ee7aae00d0f33 · report
image_coordinates ailingzengzzz/Split-and-Recombine-Net/common/transformation/cam_utils.py official repository unverified Apache-2.0 (permissive) · 2c8338c89fe8975c · report
mpjae ailingzengzzz/Split-and-Recombine-Net/common/common_pytorch/loss/loss_family.py official repository unverified Apache-2.0 (permissive) · 74396e4069c4e8d6 · report
mpjpe_smooth ailingzengzzz/Split-and-Recombine-Net/common/common_pytorch/loss/loss_family.py official repository unverified Apache-2.0 (permissive) · b72379b0ad4e784a · report
normalize_screen_coordinates ailingzengzzz/Split-and-Recombine-Net/common/transformation/cam_utils.py official repository unverified Apache-2.0 (permissive) · e53a897a491c4627 · report
process_3d ailingzengzzz/Split-and-Recombine-Net/common/transformation/aug_rotate.py official repository unverified Apache-2.0 (permissive) · 44aeda9bcbffef2a · report
rotate ailingzengzzz/Split-and-Recombine-Net/common/transformation/aug_rotate.py official repository unverified Apache-2.0 (permissive) · fb05d05fdb09695a · report
wrap ailingzengzzz/Split-and-Recombine-Net/common/common_pytorch/utils.py official repository unverified Apache-2.0 (permissive) · 5323ac47f72a7095 · report

Tasks

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M SRNet (T=243) Average MPJPE (mm) 44.8 #40 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SRNet (T=243) Multi-View or Monocular Monocular #40 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SRNet (T=243) Using 2D ground-truth joints No #40 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SRNet (T=1) Average MPJPE (mm) 49.9 #63 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SRNet (T=1) Multi-View or Monocular Monocular #63 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SRNet (T=1) Using 2D ground-truth joints No #63 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP SRNET AUC 43.8 #94 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP SRNET PCK 77.6 #94 of 108 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SRNET Average MPJPE (mm) 49.9 #22 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SRNET Frames Needed 1 #22 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SRNET Need Ground Truth 2D Pose No #22 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SRNET Use Video Sequence No #22 of 52 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