Papers › DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation

DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation

16 Mar 2022arXiv:2203.08713archive 2025-07-28

Ailing Zeng, Xuan Ju, Lei Yang, Ruiyuan Gao, Xizhou Zhu, Bo Dai, Qiang Xu

This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch. Unlike current solutions that estimate each frame in a video, DeciWatch introduces a simple yet effective sample-denoise-recover framework that only watches sparsely sampled frames, taking advantage of the continuity of human motions and the lightweight pose representation. Specifically, DeciWatch uniformly samples less than 10% video frames for detailed estimation, denoises the estimated 2D/3D poses with an efficient Transformer architecture, and then accurately recovers the rest of the frames using another Transformer-based network. Comprehensive experimental results on three video-based human pose estimation and body mesh recovery tasks with four datasets validate the efficiency and effectiveness of DeciWatch. Code is available at https://github.com/cure-lab/DeciWatch.

PaperPDFCodeCode 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="2203.08713")

Code

Syntology Ran 1 of 8 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 8 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.

cure-lab/DeciWatch officialmentioned in papermentioned 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

8 samples harvested; 1 ran; 0 honoured the contract we drafted; 7 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
7unverified

Licence: 0 of the 8 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 cure-lab/DeciWatch. “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.

qrot cure-lab/DeciWatch/lib/utils/cam_utils.py official repository ran Apache-2.0 (permissive) · 34067eef72357f72 · report
batch_compute_similarity_transform_torch cure-lab/DeciWatch/lib/utils/eval_metrics.py official repository unverified Apache-2.0 (permissive) · 1a2906773e636ce9 · report
build_model cure-lab/DeciWatch/lib/models/deciwatch.py official repository unverified Apache-2.0 (permissive) · 5c5604eb9db2dc11 · report
calculate_mpjpe cure-lab/DeciWatch/lib/utils/eval_metrics.py official repository unverified Apache-2.0 (permissive) · c49c4d20e89f777f · report
compute_error_accel cure-lab/DeciWatch/lib/utils/eval_metrics.py official repository unverified Apache-2.0 (permissive) · bfb5bcc5d76b73d1 · report
image_coordinates cure-lab/DeciWatch/lib/utils/cam_utils.py official repository unverified Apache-2.0 (permissive) · 2c8338c89fe8975c · report
normalize_screen_coordinates cure-lab/DeciWatch/lib/utils/cam_utils.py official repository unverified Apache-2.0 (permissive) · e53a897a491c4627 · report
update_cfg cure-lab/DeciWatch/lib/core/config.py official repository unverified Apache-2.0 (permissive) · f0ba038b51ec3afb · report

Tasks

2D Human Pose Estimation3D Human Pose Estimation3D Pose Estimation3D Shape Reconstruction from VideosPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation JHMDB (2D poses only) DeciWatch PCK 98.8 #1 of 5 Archive leaderboard report
3D Human Pose Estimation 3DPW DeciWatch-PARE MPJPE 75.5 #70 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW DeciWatch-PARE PA-MPJPE 46.4 #70 of 119 Archive leaderboard report
3D Human Pose Estimation AIST++ DeciWatch MPJPE 67.2 #4 of 5 Archive leaderboard report
3D Human Pose Estimation AIST++ DeciWatch Single-view Y #4 of 5 Archive leaderboard report
Pose Estimation J-HMDB DeciWatch Mean PCK@0.05 80.6 #2 of 5 Archive leaderboard report
Pose Estimation J-HMDB DeciWatch Mean PCK@0.1 94.6 #2 of 5 Archive leaderboard report
Pose Estimation J-HMDB DeciWatch Mean PCK@0.2 99.0 #2 of 5 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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