AI Paper Atlas

Research map / 3D vision / Human pose estimation

HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning

Eugene Valassakis, Guillermo Garcia-Hernando

ECCV 2024 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 1 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
back-propagate camera-space loss through differentiable global positioning (add DGP training) (ablation)HandDGP · HO3D-v2CS-MVE (mm): 85.4 -> 50.3Improved
add input image rectification to a canonical camera (ablation)HandDGP without DGP · HO3D-v2CS-MVE (mm): 121.6 -> 85.4Improved
add image rectification to DGP (ablation)HandDGP · FreiHANDRS-MVE (mm): 6.9 -> 7.6Hurt
add image rectification to DGP (ablation)HandDGP · FreiHANDCS-MVE (mm): 49.4 -> 46.3Improved
learn keypoint confidence weights instead of fixing to 1.0 (ablation)HandDGP · Human3.6MCS-MVE (mm): 174.0 -> 162.0Improved
learn keypoint confidence weights instead of fixing to 1.0 (ablation)HandDGP · HO3D-v2CS-MVE (mm): 50.4 -> 50.3No clear effect
use learned RootNet or root regression instead of geometric root findingbaseline root-relative model · FreiHANDCS-MVE (mm): 50.0 -> 62.5 (RootNet), 81.8 (root regression)Hurt
use DLT at test time versus PnP or optimizationbaseline · FreiHANDCS-MVE (mm): 50.0 vs 50.2 (PnP) vs 50.3 (Optimization)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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