AI Paper Atlas

Research map / 3D vision / Depth and stereo

Fast Two-View Motion Segmentation Using Christoffel Polynomials

Bengisu Ozbay, Octavia Camps, Mario Sznaier

ECCV 2022 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 4 citations (OpenAlex)

Read the paper

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
raise the outlier ratio from 0.9 to 1.5 (ablation)Christoffel motion segmentation · Hopkins with outlierssegmentation error (%): 7.79 -> 9.37Hurt
raise the outlier ratio from 0.9 to 2.1 (ablation)Christoffel motion segmentation · Hopkins with outlierssegmentation error (%): 7.79 -> 10.72Hurt
use frames 1 and 10 instead of 1st and last frame (smaller displacement) (ablation)Christoffel motion segmentation · Hopkins-cleansegmentation error (%): 7.4 -> 9.9Hurt
use frames 1 and 10 instead of 1st and last frame (smaller displacement) (ablation)RPA · Hopkins-cleansegmentation error (%): 6.4 -> 5.5Improved
replace RPA with the proposed methodsegmentation pipeline · BCD (3 motions)processing time per scene (s): 210 -> 0.09Improved
replace RPA with the proposed methodsegmentation pipeline · Adelaide-Fsegmentation error (%): 5.49 -> 4.15Improved
replace CBS with the proposed methodsegmentation pipeline · Adelaide-Fprocessing time per scene (s): 0.69 -> 0.02Improved
replace RPA with the proposed methodsegmentation pipeline · KT3Dsegmentation error (%): 46.4 -> 17.2Improved
replace P-x with the proposed methodsegmentation pipeline · KT3Dsegmentation error (%): 15.0 -> 17.2Hurt
replace P-xp with the proposed methodsegmentation pipeline · Hopkins-cleansegmentation error (%): 32.2 -> 7.42Improved
replace RPA with the proposed methodsegmentation pipeline · Pairwisesegmentation error (%): 2.63 -> 4.93Hurt
go from two to three motions per sceneChristoffel motion segmentation · Hopkins-cleansegmentation error (%)Hurt

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