AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Parametric Object Motion From Blur

CVPR 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 20 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use the proposed parametric motion model and segmentation instead of [4]Object motion estimation · Synthetic non-uniform motionsegmentation score (IoU): 0.33 -> 0.43Helped
Use the proposed parametric motion model instead of [4]Object motion estimation · Synthetic non-uniform motionmotion error (AEP): 13.37 -> 7.43Helped
Use the proposed method instead of [4]Object motion estimation · Synthetic uniform motionsegmentation score (IoU): 0.53 -> 0.50Hurt
Use the proposed method instead of [4]Object motion estimation · Synthetic uniform motionmotion error (AEP): 3.84 -> 4.81Hurt
Use the proposed method instead of [7]Object motion estimation · Synthetic uniform motionmotion error (AEP): 17.21 -> 4.81Helped
Use the proposed method instead of [7]Object motion estimation · Synthetic non-uniform motionmotion error (AEP): 15.06 -> 7.43Helped
Add foreground and background color models to refine the segmentation in image space (ablation)Two-stage motion estimation · Motion-blurred imagessegmentation accuracyHelped

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