Papers › Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation

Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation

6 Sep 2021ICCV 2021 10arXiv:2109.02303archive 2025-07-28

Ziniu Wan, Zhengjia Li, Maoqing Tian, Jianbo Liu, Shuai Yi, Hongsheng Li

3D human shape and pose estimation is the essential task for human motion analysis, which is widely used in many 3D applications. However, existing methods cannot simultaneously capture the relations at multiple levels, including spatial-temporal level and human joint level. Therefore they fail to make accurate predictions in some hard scenarios when there is cluttered background, occlusion, or extreme pose. To this end, we propose Multi-level Attention Encoder-Decoder Network (MAED), including a Spatial-Temporal Encoder (STE) and a Kinematic Topology Decoder (KTD) to model multi-level attentions in a unified framework. STE consists of a series of cascaded blocks based on Multi-Head Self-Attention, and each block uses two parallel branches to learn spatial and temporal attention respectively. Meanwhile, KTD aims at modeling the joint level attention. It regards pose estimation as a top-down hierarchical process similar to SMPL kinematic tree. With the training set of 3DPW, MAED outperforms previous state-of-the-art methods by 6.2, 7.2, and 2.4 mm of PA-MPJPE on the three widely used benchmarks 3DPW, MPI-INF-3DHP, and Human3.6M respectively. Our code is available at https://github.com/ziniuwan/maed.

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="2109.02303")

Code

Syntology Ran 0 of 18 code samples harvested from 1 repository linked to this paper; 18 have no recorded run.

By repository: official repository: 18 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ziniuwan/maed 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

18 samples harvested; 0 ran; 0 honoured the contract we drafted; 18 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.

18unverified

Licence: 0 of the 18 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 ziniuwan/maed. “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.

batch_adv_disc_l2_loss ziniuwan/maed/lib/core/loss.py official repository unverified MIT (permissive) · cebcdf7656167a7a · report
batch_encoder_disc_l2_loss ziniuwan/maed/lib/core/loss.py official repository unverified MIT (permissive) · 76d15c59d361a653 · report
calc_kpt_bound ziniuwan/maed/lib/data_utils/penn_action_utils.py official repository unverified MIT (permissive) · 6efb777aa4ff1f29 · report
concat_mask ziniuwan/maed/lib/core/loss.py official repository unverified MIT (permissive) · feb703d44821fb72 · report
convert_kps_to_mask ziniuwan/maed/lib/data_utils/kp_utils.py official repository unverified MIT (permissive) · b4f1af8f64e4c25f · report
get_bbox_from_kp2d ziniuwan/maed/lib/data_utils/img_utils.py official repository unverified MIT (permissive) · ac0501b71e5ef134 · report
get_img_name ziniuwan/maed/lib/data_utils/insta_utils.py official repository unverified MIT (permissive) · b21bf2eb84721e30 · report
keypoint_2d_hflip ziniuwan/maed/lib/data_utils/kp_utils.py official repository unverified MIT (permissive) · 100745c3a1bc859c · report
keypoint_3d_hflip ziniuwan/maed/lib/data_utils/kp_utils.py official repository unverified MIT (permissive) · 9df8f844f3c2fae1 · report
load_mat ziniuwan/maed/lib/data_utils/penn_action_utils.py official repository unverified MIT (permissive) · 8782aa2b6f3ea9ce · report
pad_image ziniuwan/maed/lib/data_utils/img_utils.py official repository unverified MIT (permissive) · 6578f5f4135e25e7 · report
read_calibration ziniuwan/maed/lib/data_utils/mpii3d_utils.py official repository unverified MIT (permissive) · 56adf5c78e74d698 · report
read_data ziniuwan/maed/lib/data_utils/penn_action_utils.py official repository unverified MIT (permissive) · 99675fb41689f0f0 · report
read_from_example ziniuwan/maed/lib/data_utils/insta_utils.py official repository unverified MIT (permissive) · e8e628d7220b85a2 · report
read_openpose ziniuwan/maed/lib/data_utils/mpii3d_utils.py official repository unverified MIT (permissive) · 6af6cb56d2933f3e · report
read_single_record ziniuwan/maed/lib/data_utils/insta_utils.py official repository unverified MIT (permissive) · f9d14d3d4b62a24b · report
split_into_chunks ziniuwan/maed/lib/data_utils/img_utils.py official repository unverified MIT (permissive) · a5af3953b1583f4d · report
update_cfg ziniuwan/maed/lib/core/config.py official repository unverified MIT (permissive) · 249e701b851ef72d · report

Tasks

3D Absolute Human Pose Estimation3D Human Pose EstimationDecoderPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation MPI-INF-3DHP MAED MPJPE 83.6 #42 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MAED PA-MPJPE 56.2 #42 of 108 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