AI Paper Atlas

Research map / 3D vision / Human pose estimation

VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations

Jiehong Lin, Zewei Wei, Yabin Zhang, Kui Jia

ICCV 2023 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 64 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
decompose rotation into viewpoint and in-plane rotations (ablation)VI-Net · REAL275mAP 5°2cm: 45.0 -> 50.0Improved
use binary classification on the sphere instead of direct regression for viewpoint rotation (ablation)VI-Net V-Branch · REAL275mAP 5°2cm: 43.1 -> 49.3Improved
split classification into separate azimuth and inclination classifiers (ablation)VI-Net V-Branch · REAL275mAP 5°2cm: 49.3 -> 50.0Improved
add feature transformation to the canonical zenith view in I-Branch (ablation)VI-Net · REAL275mAP 5°2cm: 33.7 -> 50.0Improved
use SPA-SConv instead of SPE-SConv spectral convolution (ablation)VI-Net · REAL275mAP 5°2cm: 35.1 -> 50.0Improved
add feature padding to SPA-SConv (ablation)VI-Net · REAL275mAP 5°2cm: 48.5 -> 50.0Improved
add symmetric (flip and max) convolution operation (ablation)SPA-SConv · REAL275mAP 5°2cm: 46.9 -> 48.5Improved
include translation and size estimation inside VI-Net instead of separate PN2 (ablation)VI-Net · REAL275mAP 5°2cm: 50.0 -> 45.0Hurt
add RGB input in addition to depth (ablation)VI-Net · REAL275mAP 5°2cm: 43.0 -> 50.0Improved
compare VI-Net (no shape priors) with shape-prior methods on CAMERA25VI-Net · CAMERA25mAP 5°2cm: VI-Net 74.1 vs SPD+CATRE 75.4Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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