Papers › A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a...

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image

27 Aug 2019ICCV 2019 10arXiv:1908.09999archive 2025-07-28

Fu Xiong, Boshen Zhang, Yang Xiao, Zhiguo Cao, Taidong Yu, Joey Tianyi Zhou, Junsong Yuan

For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed. Within A2J, anchor points able to capture global-local spatial context information are densely set on depth image as local regressors for the joints. They contribute to predict the positions of the joints in ensemble way to enhance generalization ability. The proposed 3D articulated pose estimation paradigm is different from the state-of-the-art encoder-decoder based FCN, 3D CNN and point-set based manners. To discover informative anchor points towards certain joint, anchor proposal procedure is also proposed for A2J. Meanwhile 2D CNN (i.e., ResNet-50) is used as backbone network to drive A2J, without using time-consuming 3D convolutional or deconvolutional layers. The experiments on 3 hand datasets and 2 body datasets verify A2J's superiority. Meanwhile, A2J is of high running speed around 100 FPS on single NVIDIA 1080Ti GPU.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1908.09999")

Code

Syntology Ran 8 of 9 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 6 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 6 ran; community (archive-listed): 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhangboshen/A2J officialmentioned in papermentioned on GitHubpytorch report
bo-zhang-cs/CACNet-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

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

6ran · fixture could not drive it
2ran
1unverified

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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

pixel2world zhangboshen/A2J/src/hands2017.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 040d92a92b91bba4 · report
pixel2world zhangboshen/A2J/src/nyu.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · cc10e1b8037e9967 · report
pixel2world zhangboshen/A2J/src/icvl.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 806361daca45ffd7 · report
world2pixel zhangboshen/A2J/src/hands2017.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · fa0aecbc15dfc1b2 · report
world2pixel zhangboshen/A2J/src/nyu.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · f14c24a9b48287f6 · report
world2pixel zhangboshen/A2J/src/icvl.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 023b8783def26837 · report
generate_anchors bo-zhang-cs/CACNet-Pytorch/CACNet.py community (archive-listed) ran MIT (permissive) · bb3c1b55b1637a8c · report
rescale_bbox bo-zhang-cs/CACNet-Pytorch/Cropping_dataset.py community (archive-listed) ran fingerprinted MIT (permissive) · e6e5c583560a04b3 · report
shift bo-zhang-cs/CACNet-Pytorch/CACNet.py community (archive-listed) unverified MIT (permissive) · 5c866a97bb0ce1d9 · report

Tasks

3D Pose EstimationDecoderDepth EstimationHand Pose EstimationPose Estimation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Pose Estimation K2HPD A2J FPS 93.78 #1 of 1 Archive leaderboard report
Depth Estimation NYU-Depth V2 A2J mAP 8.61 #17 of 17 Archive leaderboard report
Hand Pose Estimation HANDS 2017 A2J Average 3D Error 8.57 #3 of 9 Archive leaderboard report
Hand Pose Estimation ICVL Hands A2J Average 3D Error 6.461 #9 of 15 Archive leaderboard report
Hand Pose Estimation ICVL Hands A2J FPS 105.06 #9 of 15 Archive leaderboard report
Hand Pose Estimation K2HPD A2J PDJ@5mm 76.3 #1 of 1 Archive leaderboard report
Hand Pose Estimation NYU Hands A2J Average 3D Error 8.61 #9 of 17 Archive leaderboard report
Hand Pose Estimation NYU Hands A2J FPS 105.06 #9 of 17 Archive leaderboard report
Pose Estimation ITOP front-view A2J Mean mAP 88.0 #5 of 7 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

ConvolutionFCNMax PoolingSPEED

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