AI Paper Atlas

Research map / 3D vision / Face and shape

Category-Level 3D Correspondence in Camera Space via Morphable Object Priors

Leonhard Sommer, Artur Jesslen, Basavaraj Sunagad, Adam Kortylewski

ECCV 2026 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 0 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 instance-specific deformation to the morphable prior (ablation)Morpheus · HouseCorr3D subset (3D modal)PCK@0.1 mean: 40.2 -> 43.7Improved
add instance-specific deformation to the morphable prior (ablation)Morpheus · HouseCorr3D subset (3D amodal)PCK@0.1 mean: 37.8 -> 40.8Improved
disentangle pose, shape and camera instead of entangled canonical/camera space (Morpheus vs MagicPony+GP++)Morpheus · HouseCorr3D subset (3D modal)PCK@0.1 mean: 7.5 -> 43.7Improved
match via morphable mesh template instead of normalized object space pose (GenPose++)Morpheus · HouseCorr3D subset (3D modal)PCK@0.1 mean: 37.0 -> 43.7Improved
evaluate amodal instead of modal correspondencesMorpheus · HouseCorr3D subsetPCK@0.1 mean: 43.7 -> 40.8Hurt
transfer Morpheus to real images (ROPE)Morpheus · ROPE real-world subset (3D@0.1)PCK@0.1: 25.1 -> 34.8 vs GP++Improved

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