AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation

Yifei Shi, Boyan Wan, Xin Xu, K. Xu

TPAMI 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 0 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 PIPS sampling instead of near-surface sampling (ablation)full method · ShapeNet-C5deg5cm accuracy: 0.51 -> 0.62Improved
add PIPS-C certainty filtering of sample points (ablation)full method · ShapeNet-C5deg5cm accuracy: 0.53 -> 0.62Improved
add PIPS-S geometric stability sampling (ablation)full method · ShapeNet-C5deg5cm accuracy: 0.57 -> 0.62Improved
add anisotropic variance in pseudo ground truth instead of scalar variance (ablation)full method · ShapeNet-C5deg5cm accuracy: 0.55 -> 0.62Improved
use SO(3)-equivariant convolutional implicit network instead of 3D-GCN (ablation)full method · ShapeNet-C5deg5cm accuracy: 0.49 -> 0.62Improved
use SO(3)-equivariant network instead of 3D-GCN on held-out poses (ablation)full method · ShapeNet-C holdout pose5deg5cm accuracy: 0.38 -> 0.61Improved
add RGB features (ablation)full method · ShapeNet-C5deg5cm accuracy: 0.59 -> 0.62Improved
increase PIPS-C voxel size from 8 to 32 (ablation)PIPS-C · ShapeNet-C5deg5cm accuracy: 0.64 -> 0.58Hurt
decrease PIPS-C voxel size from 8 to 4 (ablation)PIPS-C · ShapeNet-C5deg5cm accuracy: 0.64 -> 0.49Hurt
lower target sparsity from 0.1 to 0.05 (ablation)PIPS-S · ShapeNet-C5deg5cm accuracy: 0.62 -> 0.52Hurt
raise positive-sample threshold from 0.5 to 0.9 (ablation)PIPS · ShapeNet-C5deg5cm accuracy: 0.62 -> 0.49Hurt
use PIPS method instead of AG-Pose (ablation)AG-Pose · NOCS-REAL2755deg2cm accuracy: 0.57 -> 0.63Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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