AI Paper Atlas

Research map / 3D vision / Human pose estimation

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek, Shreyas Hampali, Mahdi Rad, Zhaohui Zhang, Shipeng Xie, MingXiu Chen, Boshen Zhang, Fu Xiong, Yang Xiao, Zhiguo Cao and 23 more

ECCV 2020 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 55 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
use segmentation-network hand center instead of threshold center (ablation)AWR (ResNet-50) · HANDS'19 Task 1 extrapolationMJE (mm): 20.70 -> 14.89Improved
crop the hand from the segmented mask instead of original depth (ablation)AWR (ResNet-50) · HANDS'19 Task 1 extrapolationMJE (mm): 14.89 -> 14.75Improved
use ResNet-101 instead of ResNet-50 backbone (ablation)AWR · HANDS'19 Task 1 extrapolationMJE (mm): 14.75 -> 14.44Improved
ensemble five models (ablation)AWR · HANDS'19 Task 1 extrapolationMJE (mm): 14.44 -> 13.67Improved
use deeper ResNet-152 instead of ResNet-101 (ablation)NLE · HANDS'19 Task 3 extrapolationMJE (mm): 32.56 -> 37.56Hurt
quadruple the kernels of V2V-PoseNet (wider) (ablation)NTIS · HANDS'19 extrapolationMJE (mm): 38.33 -> 36.36Improved
increase number of anchor poses from 1 to 50 (ablation)NLE · HANDS'19 Task 3 shape extrapolationMJE (mm): 21.08 -> 16.55Improved
add joint 2D pose learning to 3D-only regression (ablation)NLE · HANDS'19 Task 3 object extrapolationMJE (mm): 37.31 -> 28.45Improved
use pose proposal integration instead of NMS (ablation)NLE · HANDS'19 Task 3 extrapolationMJE (mm): 38.08 -> 34.63Improved
ensemble 12 rotated test images instead of 1 (ablation)NLE · HANDS'19 Task 3 shapeMJE (mm): 17.35 -> 15.79Improved
ensemble the four input-type models (ablation)Strawberryfg · HANDS'19 Task 1 extrapolationMJE (mm): 21.19 -> 19.63Improved
add local patch refinement and volume rendering supervision (ablation)Strawberryfg model 4 · HANDS'19 Task 1 extrapolationMJE (mm): 22.56 -> 21.19Improved

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