AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation

Qichen Fu, Xingyu Liu, Ran Xu, Juan Carlos Niebles, Kris M. Kitani

ICCV 2023 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 34 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
add Dynamic Fusion Module over frame-wise center prediction (ablation)Deformer · DexYCB (All)MPJPE (mm): 5.72 -> 5.22Improved
learned dynamic confidence instead of simple average of deformed predictions (ablation)Deformer · DexYCB (All)MPJPE (mm): 5.40 -> 5.22Improved
learned confidence instead of occlusion-level weighting (ablation)Deformer · DexYCB (Occlusion 75%-100%)MPJPE (mm): 6.33 -> 6.34No clear effect
add Dynamic Fusion Module on HO3D (ablation)Deformer · HO3DJoint error (mm): 9.8 -> 9.4Improved
replace MSE with maxMSE loss (ablation)Deformer · DexYCB (All)MPJPE (mm): 5.63 -> 5.22Improved
add maxMSE loss with no discriminator (ablation)Deformer · DexYCB (All)MPJPE (mm): 5.72 -> 5.43Improved
add motion discriminator (adversarial training) (ablation)Deformer · DexYCB (All)MPJPE (mm): 5.43 -> 5.22Improved
add motion discriminator without maxMSE (ablation)Deformer · DexYCB (All)MPJPE (mm): 5.72 -> 5.63Improved
Deformer versus best monocular method on HO3DDeformer · HO3DJoint error (mm): 9.4 vs 9.1Hurt

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