AI Paper Atlas

Research map / 3D vision / Human pose estimation

Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation

Nassim Ali Ousalah, Peyman Rostami, Vincent Gaudillière, Emmanuel Koumandakis, Anis Kacem, Enjie Ghorbel, Djamila Aouada

CVPR 2026 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 2 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 SPD manifold head instead of Euclidean MLP head (ablation)Cov2Pose · LM-OADD(-S): 31.0 -> 76.8Improved
use spatial covariance instead of channel covariance (ablation)Cov2Pose · LM-OADD(-S): 70.9 -> 76.8Improved
add Cholesky pose decoding with SO(3) loss instead of log-tangent-space training (ablation)Cov2Pose · LM-OADD(-S): 72.3 -> 76.8Improved
use 6D rotation with Gram-Schmidt (4x4 SPD) instead of Euler angles (3x3 SPD) (ablation)Cov2Pose · LM-OADD(-S): 70.9 -> 76.8Improved
Cov2Pose vs indirect PnP methodsCov2Pose · LMADD(-S): 97.1 -> 97.2No clear effect
Cov2Pose vs ZebraPose on occlusionCov2Pose · LM-OADD(-S): 76.9 -> 76.8No clear effect
Cov2Pose vs GDR-Net on YCB-V AUCCov2Pose · YCB-VAUC of ADD(-S): 84.4 -> 82.2Mixed

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