AI Paper Atlas

Research map / 3D vision / Human pose estimation

Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects

Zicong Fan, Takehiko Ohkawa, Linlin Yang, Nie Lin, Zhishan Zhou, Shihao Zhou, Jiajun Liang, Zhong Gao, Xuanyang Zhang, Xue Zhang, Fei Li, Liu Zheng and 12 more

ECCV 2024 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 22 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 perspective crop with virtual camera to reduce fisheye-rectified distortionAssemblyHands hand pose methods · AssemblyHands testMPJPE (mm): baseline 20.31 -> 24.85 from center to edge; method 1 stays 12.35 -> 13.72Improved
average four egocentric views instead of two lower views (ablation)AssemblyHands baseline · AssemblyHands testMPJPE (mm): 21.52 -> 20.69Improved
fuse multiple views by simple average instead of single view (ablation)AssemblyHands baseline · AssemblyHands testMPJPE (mm): 22.19 -> 21.52Improved
use adaptive view selection and high-capacity backbone (Hiera, RegNetY320) in place of ResNet50 baselineAssemblyHands · AssemblyHands testMPJPE (mm): 20.69 -> 12.21 and 12.46Improved
scale frozen ViT backbone from ViT-L to ViT-G (ablation)transformer decoder method on ARCTIC · ARCTIC allocentric validationCDev (mm): 30.5 -> 29.0Improved
replace MLP regressors with transformer decoder and frozen DINOv2 ViT-G backboneArcticNet-SF · ARCTIC allocentric testCDev (mm): 41.56 -> 27.97Improved
add Swin-L Deformable DETR method with incomplete trainingArcticNet-SF · ARCTIC allocentric testCDev (mm): 41.56 -> 64.15Hurt
evaluate from egocentric view rather than allocentric viewARCTIC methods · ARCTIC testhand pose error vs object errorMixed

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