AI Paper Atlas

Research map / Video / Video segmentation and tracking

3D Rigid Motion Segmentation with Mixed and Unknown Number of Models

Xun Xu, Loong‐Fah Cheong, Zhuwen Li

TPAMI 2019 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 46 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
fuse affine, homography and fundamental affinities via subset constrained clustering (ablation)single-model motion segmentation · Hopkins155classification error (%): 0.59 -> 0.31Improved
fuse models with co-regularization instead of single homography (ablation)homography model · Hopkins155classification error (%): 0.71 -> 0.46Improved
fuse models with subset constrained clustering (ablation)best single model · KT3DMoSegmean classification error (%): 11.45 -> 8.08Improved
fuse models with co-regularization (ablation)best single model · KT3DMoSegmean classification error (%): 11.45 -> 7.92Improved
fuse models with subset constrained clustering (ablation)affine model · MTPV62classification error (%): 0.82 -> 0.65Improved
use fundamental matrix instead of affine as single model (ablation)single-model motion segmentation · Hopkins155classification error (%): 0.59 -> 1.79Hurt
use affine model instead of homography on strong perspective data (ablation)single-model motion segmentation · KT3DMoSegmean classification error (%): 11.45 -> 15.76Hurt
use homography model for model selection with 2 to Mmax candidates over 1 to Mmax (ablation)NCRE model selection · Hopkins155correct rate (%): 87.10 -> 92.26Improved
replace MSSC with NCRE homography model selectionMSSC · Hopkins155correct rate (%): 85.81 -> 92.26Improved
fuse three models for model selection instead of single homography (ablation)NCRE model selection · Hopkins155classification error (%): 3.95 -> 3.17Improved
fuse three models for model selection instead of single homography (ablation)NCRE model selection · Hopkins155correct rateNo clear effect
replace MSSC with NCRE affine modelMSSC · MTPV62classification error (%): 5.09 -> 2.78Improved

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