AI Paper Atlas

Research map / 3D vision / Gaussian splatting

PoseGaussian: 6D Pose Estimation for Unseen Objects via Sparse-View Object-Level 3D Gaussian Splatting

Wubin Shi, Shaoyan Gai, Feipeng Da

CVPR 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS

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 adaptive density control (ablation)PoseGaussian · LinemodPose ACC: 85.0 -> 87.5Improved
add view-warping augmentation (ablation)PoseGaussian · LinemodPose ACC: 85.9 -> 87.5Improved
use improved 3DGS (depth prior init and sparse training) instead of vanilla 3DGS (ablation)PoseGaussian · LinemodPose ACC: 82.1 -> 87.5Improved
use two-stage learning-guided ICP initializer instead of Gen6D selector (ablation)PoseGaussian · LinemodPose ACC: 68.7 -> 87.5Improved
use two-stage learning-guided ICP initializer instead of Cas6D selector (ablation)PoseGaussian · LinemodPose ACC: 71.4 -> 87.5Improved
use 3DGS differentiable rendering refiner instead of learning-based Gen6D refiner (ablation)PoseGaussian · LinemodPose ACC: 79.2 -> 87.5Improved
reduce reference views from over 200 to 8 (ablation)PoseGaussian · Linemod ADD(S)-0.1d meanADD(S)-0.1d mean: 87.2 -> 54.30Hurt
use 8 reference views instead of 16 for baselines (comparison with Gen6D/Cas6D/OnePose++ at 16 views)PoseGaussian · Linemod (sparse views)ADD(S)-0.1d mean: 54.30 vs 47.83 (Cas6D, 16 views)Improved
use 8 reference views while baselines use 16 viewsPoseGaussian · GenMOPADD-0.1d average: 27.56 vs 37.01 (Cas6D, 16 views)Hurt
add depth structural prior and sparse training strategy to 3DGS under few views (ablation)3DGS reconstruction · Linemod, 8-32 viewspose accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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