AI Paper Atlas

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

Soft-Segmentation Guided Object Motion Deblurring

CVPR 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 108 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 joint soft-segmentation and deblurringObject motion deblurring on synthetic images · Synthetic images (16-image average)PSNR: 21.66 -> 22.79Helped
initialize segmentation with rectangular bounding boxes instead of convex hulls around seed points (ablation)Soft-Segmentation Guided Object Motion Deblurring · Real object motion deblurring examplesvisual deblurring qualityNo clear effect
use the matting Laplacian in (7) instead of the affinity matrix in (6) (ablation)Soft-Segmentation Guided Object Motion Deblurring · Object motion deblurringvisual deblurring qualityHelped
remove soft-segmentation guidance (ablation)Object motion deblurring · Object motion deblurringvisual deblurring qualityHurt

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