AI Paper Atlas

Research map / 3D vision / Human pose estimation

Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold

Kieran A Murphy, Carlos Esteves, Varun Jampani, Srikumar Ramalingam, Ameesh Makadia

ICML 2021 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 7 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 an implicit, non-parametric pose distribution instead of the compared parameterized distribution baselinespose estimation · SYMSOL Iaverage log likelihood: -0.43 -> 4.1Improved
Use an implicit, non-parametric pose distribution instead of the compared parameterized distribution baselinespose estimation · SYMSOL IIaverage log likelihood: 3.7 -> 7.57Improved
Return top-2 pose candidates rather than only the top-1 predictionIPDF · ModelNet10-SO(3)Acc@15°: 0.719 -> 0.868Improved
Return top-2 pose candidates rather than only the top-1 predictionIPDF · ModelNet10-SO(3)median angle error: 21.5 -> 4.9Improved
Use an implicit, non-parametric pose distribution instead of the compared methodspose estimation · T-LESSlog likelihood: 8.8 -> 9.80Improved
Use an implicit, non-parametric pose distribution instead of the compared methodspose estimation · T-LESSspread (°): 3.44 -> 4.12Mixed
Use 50,000 rather than 10,000 training images per shape (ablation)IPDF · SYMSOL Iaverage log likelihoodImproved
Add positional encoding to rotation queries (ablation)IPDF · SYMSOL I discrete-symmetry shapesaverage log likelihoodImproved
Add positional encoding to rotation queries (ablation)IPDF · SYMSOL I cone and cylinderaverage log likelihoodMixed
Represent query rotations as matrices rather than axis-angle or quaternions (ablation)IPDF · SYMSOL Iaverage log likelihoodImproved
Represent query rotations as Euler angles (ablation)IPDF · SYMSOL Iaverage log likelihoodHurt
Use randomly sampled rotations rather than an equivolumetric grid for training-time normalization (ablation)IPDF · SYMSOL Iaverage log likelihoodNo clear effect

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