AI Paper Atlas

Research map / 3D vision / Human pose estimation

Generic 3D Representation via Pose Estimation and Matching

Amir R. Zamir, Tilman Wekel, Pulkit Agrawal, Colin Wei, Jitendra Malik, Silvio Savarese

ECCV 2016 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 74 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 Euler angles instead of quaternions (ablation)pose ConvNet · Street view test set (pose estimation)median angular error (deg): 29.8 -> 17.7Improved
use robust loss instead of l2 loss (ablation)pose ConvNet · Street view test set (pose estimation)median angular error (deg): 22.3 -> 17.7Improved
train jointly on matching and pose (ablation)joint descriptor · Street view test setsmatching and pose accuracyNo clear effect
use gradient clipping (ablation)pose ConvNet · trainingtraining stabilityImproved
use our representation instead of AlexNet Pool5 for NN layout classificationfrozen representation · LSUN layout classificationaccuracy (%): 47.7% -> 57.6%Improved
use our frozen representation instead of training from scratchPASCAL3D pose · PASCAL3D pose estimationaverage pose error (deg): 34 -> 26Improved
use our representation instead of ImageNet AlexNetPASCAL3D pose · PASCAL3D pose estimationaverage pose error (deg): 23 -> 26Hurt
use our descriptor instead of siam on Brown benchmarkdescriptor matching · Brown benchmark (mean)FPR@95 (%): 10.07 -> 8.46Improved
use our descriptor on small-baseline Lib to Yos transferdescriptor matching · Brown benchmark (train Lib, test Yos)FPR@95 (%): 11.18 -> 13.78Hurt
use our unsupervised representation vs supervised Hedau et al. for layoutfrozen representation · LSUN layout estimationcorner error: 0.15 -> 0.16Hurt

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