AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Linearly Converging Quasi Branch and Bound Algorithms for Global Rigid Registration

Nadav Dym, Shahar Ziv Kovalsky

ICCV 2019 · Learning theory and algorithms › Sample complexity · approach: Statistical-query lower bounds · 11 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
replace linear BnB lower bounds with quadratic quasi-lower boundsGo-ICP BnB for rigid-CP · Synthetic rigid-CP, high accuracy or noisefunction evaluations: Go-ICP grows rapidly; qBnB stabilizes at almost constant 10^6 evaluationsImproved
use qBnB instead of Go-ICP at low noise and low accuracyrigid-CP · Synthetic rigid-CPfunction evaluationsNo clear effect
use qBnB instead of Go-ICP on noisy bunny registrationrigid-CP · Stanford bunny, sigma=0.1run time: over 6 hours -> under 7 minutesImproved
use qBnB instead of BFS BnB on 2D frog silhouettesrigid bijective · 2D frog silhouettes, 50 pointsrun time (seconds): 11 -> 0.5Improved
use qBnB instead of BFS BnB on 3D chairsrigid bijective · 3D chair meshes, 50 pointsconvergence: over 1 hour, not converged -> 6.5 secondsImproved
use qBnB instead of Auto3dgm pairwise matchingmorphology alignment · Ateles teeth, 200 pointsalignment energy and run time: ~ 3 seconds -> 2-5 minutesMixed

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