AI Paper Atlas

Research map / 3D vision / Human pose estimation

HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation

WENCAN CHENG, Eunji Kim, Jong Hwan Ko

ECCV 2024 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace no attention with conventional dot-product softmax attention (ablation)HandDAGT decoder · NYUmean keypoint error (mm): 7.43 -> 10.66Hurt
use sigmoid Hadamard attention instead of conventional softmax attention (ablation)HandDAGT decoder · NYUmean keypoint error (mm): 10.38 -> 7.12Improved
add enhanced queries and keys (ablation)HandDAGT decoder · NYUmean keypoint error (mm): 7.30 -> 7.12Improved
add kinematic topology attention to local-point attention (ablation)HandDAGT decoder · NYUmean keypoint error (mm): 7.24 -> 7.12Improved
add local-point attention to kinematic topology attention (ablation)HandDAGT decoder · NYUmean keypoint error (mm): 7.21 -> 7.12Improved
add denoising training (ablation)HandDAGT · NYUmean keypoint error (mm): 7.20 -> 7.12Improved
stack 3 transformers instead of 1 (ablation)HandDAGT · NYUmean keypoint error (mm): 8.02 -> 7.12Improved
stack 3 transformers instead of 2 (ablation)HandDAGT · NYUmean keypoint error (mm): 7.15 -> 7.12No clear effect
increase input patch size from 64 to 128 super points (ablation)HandDAGT · NYUmean keypoint error (mm): 7.12 -> 7.16Hurt
reduce input patch size from 64 to 32 super points (ablation)HandDAGT · NYUmean keypoint error (mm): 7.12 -> 7.20Hurt
use HandDAGT instead of IPNet on HO3Dhand-object pose estimation · HO3D_v2mean keypoint error (mm): 1.81 -> 1.81No clear effect

Later papers that compared with this method

1 later accepted paper reports HandDAGT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy