AI Paper Atlas

Research map / 3D vision / Depth and stereo

Capturing Dynamic Textured Surfaces of Moving Targets

Ruizhe Wang, Lingyu Wei, Etienne Vouga, Qixing Huang, Duygu Ceylan, Gérard Medioni, Hao Li

ECCV 2016 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 36 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
use visibility-error-metric PSO registration instead of 4PCSglobal registration · Stanford 3D Scanning Repositorysuccess rate (%): 73.0 -> 93.6Improved
use visibility-error-metric PSO registration instead of 4PCSglobal registration · Princeton Shape Benchmarksuccess rate (%): 73.2 -> 81.5Improved
use visibility-error-metric PSO registration instead of 4PCSglobal registration · Stanford 3D Scanning Repositoryaverage runtime (sec): 10 -> 0.5Improved
use visibility-error-metric PSO registration instead of FPFHglobal registration · Stanford 3D Scanning Repositorysuccess rate (%): 49.3 -> 93.6Improved
use visibility-error-metric PSO registration instead of Go-ICPglobal registration · Stanford 3D Scanning Repositorysuccess rate (%): 34.1 -> 93.6Improved
use visibility-error-metric PSO registration instead of PCA axes alignmentglobal registration · Princeton Shape Benchmarksuccess rate (%): 18.5 -> 81.5Improved
add guide particles (Levenberg-Marquardt) to traditional PSO (ablation)modified PSO registration · Stanford 3D Scanning Repositorysuccess rateImproved
add swarm displacement of regular particles on top of guide-particle updates (ablation)guide-particle-only registration · Stanford 3D Scanning Repository (overlap below 30%)success rateImproved
add PSO optimization on top of picking the minimum-VEM initial particle (ablation)registration with initial particles only · Stanford 3D Scanning Repositorysuccess rateImproved
reduce overlap between scans below 40%previous global registration methods · Stanford and Princetonsuccess rateHurt
reduce overlap between scans below 15%visibility-error-metric registration · Stanford and Princetonsuccess rateHurt
use dense-correspondence texture transfer instead of direct texture stitchingtexture reconstruction · captured sequencestexture qualityImproved

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