AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Closed-Form, Pairwise Solution to Local Non-Rigid Structure-From-Motion

Shaifali Parashar, Yuxuan Long, Mathieu Salzmann, Pascal Fua

TPAMI 2024 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 6 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
solve for surface normals in closed form instead of global joint optimizationCh17 (global NRSfM) · Paper/Rug (350 correspondences)run time: about 150 times faster than Ch17Improved
use two-solution closed-form normals instead of polynomial solversPa19 (local method) · Paper/Rugrun time: 50 times faster than Pa19Improved
add degeneracy measure (sigma1/sigma3 > 1.05) to discard unreliable normals (ablation)Ours · NRSfM challenge dataset3D error EdImproved
reconstruct jointly from multiple images instead of pairwise (ablation)Ours · synthetic surfacesreconstruction accuracyImproved
smooth normals via integration (ablation)Ours versus Ch14, Va09 · synthetic surfacesnormal errorMixed
use Ours instead of Ch17 and Ji17global baselines · TshirtEdHurt

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