AI Paper Atlas

Research map / 3D vision / Depth and stereo

Motion Segmentation by Exploiting Complementary Geometric Models

Xun Xu, Loong Fah Cheong, Zhuwen Li

CVPR 2018 · 3D vision › Depth and stereo · approach: Camera model and calibration for SfM · 39 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 the affine, homography, and fundamental-matrix views with subset constraints instead of using one geometric modelMotion segmentation · Hopkins155classification error (%): 0.59 -> 0.31Improved
Fuse the affine, homography, and fundamental-matrix views with kernel addition instead of using one geometric modelMotion segmentation · Hopkins155classification error (%): 0.59 -> 0.36Improved
Use subset-constrained fusion rather than the single affine viewMotion segmentation · Hopkins12classification error (%): 0.15 -> 0.06Improved
Use subset-constrained fusion rather than the single affine viewMotion segmentation · MTPV62 perspective (9 clips)classification error (%): 0.25 -> 0.20Improved
Use multi-view co-regularization rather than the single homography viewMotion segmentation · KT3DMoSegaverage classification error (%): 11.45 -> 7.92Improved
Use multi-view co-regularization rather than the single homography viewMotion segmentation · KT3DMoSegmedian classification error (%): 7.14 -> 0.75Improved
Replace subset-constrained fusion with co-regularization (ablation)Multi-view spectral clustering · Hopkins155classification error (%): 0.31 -> 0.46Hurt
Replace subset-constrained fusion with kernel addition (ablation)Multi-view spectral clustering · Hopkins155classification error (%): 0.31 -> 0.36Hurt
Use the fundamental-matrix view alone instead of fused views (ablation)Motion segmentation · Hopkins155classification error (%): 0.31 -> 1.79Hurt
Use the fundamental-matrix view alone instead of fused views (ablation)Motion segmentation · MTPV62 perspective (9 clips)classification error (%): 0.20 -> 5.09Hurt
Vary co-regularization strength to modify the fundamental-matrix view (ablation)Co-regularized F-view · KT3DMoSegclassification error (%)Mixed

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