AI Paper Atlas

Research map / 3D vision / Human pose estimation

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation

Fulin Liu, Yinlin Hu, Mathieu Salzmann

ICCV 2023 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 14 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 LC loss to GDR-Net (ablation)GDR-Net · LM-OADD(-S): 59.29 -> 66.48Improved
add LC loss to ZebraPoseZebraPose · YCB-VADD(-S): 80.5 -> 82.4Improved
add LC loss to GDR-NetGDR-Net · YCB-VADD(-S): 60.1 -> 70.6Improved
add the covariance term E_cov (ablation)LC loss on GDR-Net · LM-OADD(-S): 45.61 -> 66.48Improved
add the prior term E_prior (ablation)LC loss on GDR-Net · LM-OADD(-S): 60.69 -> 66.48Improved
keep residuals attached (not detached) in E_cov (ablation)LC loss on GDR-Net · LM-OADD(-S): 61.03 -> 66.48Improved
keep weights attached (not detached) in E_cov (ablation)LC loss on GDR-Net · LM-OADD(-S): 65.23 -> 66.48Improved
add the linear loss term E_linear (ablation)LC loss on GDR-Net · LM-OADD(-S): 65.82 -> 66.48Improved
use 2D image-space pose representation instead of 3D (ablation)LC loss on GDR-Net · LM-OADD(-S): 66.48 -> 65.99No clear effect
replace Laplace NLL with Gaussian NLL (ablation)LC loss on GDR-Net · LM-OADD(-S): 66.48 -> 61.90Hurt
use quaternion, axis-angle or two-column pose representation instead of 3D (ablation)LC loss (Laplace) · LM-OADD(-S): 66.48 vs 66.72, 65.85, 66.39No clear effect
add LC loss to sparse correspondence baseline with weighted PnP (ablation)sparse MLE baseline · LM-OADD(-S): 59.90 -> 61.08Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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