AI Paper Atlas

Research map / 3D vision / Depth and stereo

Generalized Closed-Form Formulae for Feature-Based Subpixel Alignment in Patch-Based Matching

Laurent Valentin Jospin, Hamid Laga, Farid Boussaïd, Mohammed Bennamoun

IJCV 2025 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 2 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 parabola cost interpolation with barycentric feature interpolationZNCC subpixel refinement · Middlebury 2014 stereo (1D, 5x5 window)MAE (px): 0.15 -> 0.12Improved
replace parabola cost interpolation with equiangular or Shimizu-Okutomi to reduce pixel lockingZNCC 5x5 cost-based refinement · Middlebury 2014 stereo (1D)pixel-locking SNR (dB): -13.14 -> -26.68Improved
use predictive interpolation (left and right features together) instead of barycentricZNCC feature-based refinement · Middlebury 2014 stereo (1D, 5x5 window)MAE (px): 0.12 -> 0.15Hurt
enlarge correlation window from 5x5 to 11x11 (ablation)ZNCC barycentric feature refinement · Middlebury 2014 stereo (1D)MAE (px): 0.12 -> 0.15Hurt
use feature-based instead of cost-based refinement for SADSAD cost · Middlebury 2014 stereo (1D, 5x5 window)MAE (px): 0.18 -> 0.19Hurt
use barycentric feature refinement instead of parabola for MedSMedS cost · Middlebury 2014 stereo (1D, 5x5 window)MAE (px): 0.20 -> 0.27Hurt
replace isotropic parabola with Queen split feature refinementZNCC subpixel refinement · Middlebury optical flow (2D, 11x11 window)mean distance (px): 0.22 -> 0.16Improved
replace isotropic parabola with Queen split feature refinementZNCC subpixel refinement · Middlebury optical flow (2D, 5x5 window)mean distance (px): 0.26 -> 0.19Improved
replace isotropic with anisotropic parabola cost refinementZNCC cost-based refinement · Middlebury optical flow (2D, 11x11 window)mean distance (px): 0.22 -> 0.27Hurt
consider all four corners symmetrically (Queen) instead of splitting featuresZNCC feature refinement · Middlebury optical flow (2D, 11x11 window)mean distance (px): 0.16 -> 0.22Hurt
use Queen split feature refinement for MedS instead of isotropic parabolaMedS cost · Middlebury optical flow (2D, 11x11 window)mean distance (px): 0.25 -> 0.34Hurt
enlarge correlation window from 5x5 to 11x11 (ablation)ZNCC Queen split feature refinement · Middlebury optical flow (2D)mean distance (px): 0.19 -> 0.16Improved

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