AI Paper Atlas

Research map / 3D vision / Human pose estimation

OrienPose: Orientation-Guided Novel View Synthesis for Single-Image Unseen Object Pose Estimation

Yating Liu, Zhaoshuai Qi, Yang Zou, Yongnan Yang, Shizhou Zhang, Yanning Zhang

CVPR 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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
inject orientation priors into the NVS latent (OAG) and add orientation consistency lossOrienPose vs NOPE · ShapeNet (10 unseen categories)ACC 30: 52.3 -> 59.6Improved
inject orientation priors into the NVS latent (OAG) and add orientation consistency lossOrienPose vs NOPE · ShapeNet (10 unseen categories)Median pose error: 27.7 -> 20.4Improved
add both OAG and orientation consistency loss L_OC (vs either alone) (ablation)OrienPose · ShapeNet busACC 30: 53.3 and 55.1 (single component) -> 58.7Improved
replace NOPE's NVS network with diffusion-based Free3DNOPE · ShapeNet (10 unseen categories)ACC 30: 52.3 -> 40.4Hurt
zero-shot transfer from synthetic ShapeNet training to real NAVI objectsNOPE · NAVIACC 30: 52.3 -> 36.8Hurt
zero-shot transfer from ShapeNet to NAVIOrienPose · ShapeNet vs NAVIACC 30: 59.6 -> 50.9Hurt
Gaussian blur of reference image up to 40% (ablation)OrienPose · ShapeNet busACC 30: 58.7 -> 56.0No clear effect
random occlusion of reference up to 40% of object area (ablation)OrienPose · ShapeNet busACC 30: 58.7 -> 53.3Hurt
occlusion of 10% and 20% of object area (ablation)OrienPose · ShapeNet busACC 30: 58.7 -> 57.2 / 56.9 (Table 3 occlusion columns)No clear effect
provide only two views (single reference) to multi-view methodsOnePose++ and BoxDreamer · ShapeNetACC 30Hurt
larger viewpoint gap (45-90 deg) between reference and queryOrienPose · NAVIqualitative pose accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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