AI Paper Atlas

Research map / 3D vision / Human pose estimation

Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding

Niloofar Azizi, Mohsen Fayyaz, Horst Bischof

ECCV 2024 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 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
add PerturbPE positional encoding to MobiusGCN (0.66M)MobiusGCN · Human3.6M Protocol #1 (2D GT)MPJPE (mm): 34.1 -> 32.7Improved
widen MobiusGCN channels from 128 to 192 (ablation)MobiusGCN · Human3.6M Protocol #1 (2D GT)MPJPE (mm): 36.2 -> 34.1Improved
use perturbed eigenvectors (0-edge, resolving multiplicity) instead of plain Laplacian eigenvectors (ablation)PerturbPE with one edge missing · Human3.6M, one edge missingMPJPE (mm): 55.0 -> 51.4Improved
average over 1-edge perturbations instead of 0-edge perturbation (ablation)PerturbPE with one edge missing · Human3.6M, one edge missingMPJPE (mm): 51.4 -> 49.0Improved
perturb with two removed edges instead of one (ablation)PerturbPE with one edge missing · Human3.6M, one edge missingMPJPE (mm): 49.0 -> 48.0Improved
add PerturbPE to MobiusGCN when two edges are missingMobiusGCN · Human3.6M, two edges missingMPJPE (mm): 60.0 -> 54.0Improved
add PerturbPE when trained with few subjects (S1 only)MobiusGCN · Human3.6M reduced training dataMPJPE (mm): 44.7 -> 42.9Improved
add PerturbPE to MobiusGCN on cross-dataset testMobiusGCN · MPI-INF-3DHPPCK (All): 80.0 -> 82.0Improved
add PerturbPE to SemGCNSemGCN · Human3.6M (2D GT)MPJPE (mm): 43.1 -> 42.0Improved
use one network with PerturbPE vs GFPose per-case networks for occluded limbsPerturbPE · Human3.6M, both arms occludedMPJPE (mm): 60.0 -> 58.6Improved
add PerturbPE (adds RSPT computation) to MobiusGCN inferenceMobiusGCN · inference time per sampleseconds: 0.009 -> 0.010Mixed

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