AI Paper Atlas

Research map / 3D vision / Depth and stereo

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann

TPAMI 2020 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 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 analytical SVD/Eigh gradients with the eigendecomposition-free lossplane fitting with a single outlier · Plane fitting (single outlier)loss decrease during optimizationImproved
replace analytical SVD/Eigh gradients with the eigendecomposition-free lossplane fitting with twenty outliers · Plane fitting (20 outliers, Adam)convergence: convergence suddenly happens after 352 iterations for SVD/EighImproved
add the eigendecomposition-free loss instead of Essential_Only eigendecomposition loss (ablation)wide-baseline stereo keypoint matching · SUN3D wide-baseline stereomAPImproved
drop the classification pre-training stage (ablation)eigendecomposition-free loss · SUN3D wide-baseline stereomAPNo clear effect
use eigendecomposition-free loss instead of REPPnPPnP outlier removal · PnP synthetic, outliers 10 to 150rotation error: more than 40 outliers, that is, 20%Improved
apply synthetic-trained model to real data without fine-tuningPnP outlier removal · PnP real data (1000 images)reprojection accuracyImproved
use eigendecomposition-free loss under combined noise and outliersPnP simultaneous denoising and outlier removal · PnP synthetic noise+outliersrotation and translation errorImproved
use eigendecomposition-free loss for denoisingellipse fitting · Ellipse fitting denoisingcenter point errorImproved

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