AI Paper Atlas

Research map / Point clouds / Registration and matching

Discriminative Optimization: Theory and Applications to Computer Vision

Jayakorn Vongkulbhisal, Fernando N. de la Torre, João Paulo Costeira

TPAMI 2018 · Point clouds › Registration and matching · approach: Quantum and certifiable correspondence · 22 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 DO learned on P4 data instead of fmincon with the matching nonconvex cost P4DO (SUM) · 1D unknown cost, test P4MAE: .0457 -> .0325Improved
use DO learned on P6 data instead of fmincon with the matching cost P6DO (SUM) · 1D unknown cost, test P6MAE: .1161 -> .0698Improved
use DO instead of fmincon with the correct convex cost P1DO (SUM) · 1D unknown cost, test P1MAE: .0000 -> .0137Hurt
use DO instead of fmincon with a mismatched cost on P3DO (SUM) · 1D unknown cost, test P3MAE: .1535 -> .0086Improved
train DO on the noise type that matches test noise (not mismatched) (ablation)DO-SP / DO-RV · Image denoising impulse noisePSNRImproved
train DO on mixed SP and RV noise (DO-SPRV) (ablation)DO · Image denoising impulse noisePSNRMixed
add DO inlier selection before P3P+RANSACP3P+RANSAC · Camera pose estimation, real imagecomputation time: 8 timesImproved
add DO inlier selection before P3P+RANSAC at high outlier ratioP3P+RANSAC · Camera pose estimation, syntheticrotation errorImproved
use DO alone for pose without geometric constraintsDO · Camera pose estimation, syntheticrotation errorHurt
replace ICP with DO for object tracking in 3D point cloudDO · 3D object tracking (kettle, hat)tracking robustness: 40ms per frameImproved
replace ICP with DO for registration on UWA range scansDO · UWA range-scan registrationsuccess rateImproved

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