AI Paper Atlas

Research map / 3D vision / Face and shape

JRM: Joint Reconstruction Model for Multiple Objects without Alignment

Qirui Wu, Yawar Siddiqui, Duncan Frost, Samir Aroudj, Armen Avetisyan, Richard Newcombe, Angel X. Chang, Jakob Engel, Henry Howard-Jenkins

CVPR 2026 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 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 joint coupled reconstruction (JRM) over independent FM with 3 rescansJRM · Temporal repetition, 3 rescansCD: 4.43 -> 3.07 (vs FM aligned by MORE2)Improved
add more rescans for FM with estimated alignmentFM · Temporal repetitionCD: 3.07 -> 4.43 (target only to 3 rescans)Hurt
add more rescans for JRMJRM · Temporal repetitionCD: 3.46 -> 2.95 (target only to 1 rescan)Improved
JRM vs FM with target scan onlyJRM · Temporal repetition, target onlyCD: 3.46 vs 3.07No clear effect
add an identical source objectJRM · Spatial repetitionCD: 2.61 -> 2.49Improved
add a negative (different) source object to FMFM · Spatial repetitionCD: 3.33 -> 8.83Hurt
add a negative source object to JRMJRM · Spatial repetitionCD: 2.61 -> 3.04Hurt
use JRM instead of FM with oracle alignment for articulated objectsJRM · Articulation state 1CD: 5.37 -> 3.66Improved
use JRM instead of FM on real scenesJRM · ScanNet++CD: 4.20 -> 2.69Improved
use JRM instead of FM on real scenesJRM · ReplicaCD: 3.74 -> 3.21Improved
train only on similar pairs (neg ratio 0 vs 0.1) (ablation)JRM · Spatial repetition, negative pairCD: 6.22 vs 2.56Hurt
train only on negative pairs (ratio 1 vs 0.1) (ablation)JRM · Spatial repetition, identical pairCD: 2.18 -> 2.69Hurt

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