atlas

Research map / Video / Video segmentation and tracking

Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework

CVPR 2018 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 205 citations (OpenAlex)

Read the paperCheck 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 SPAC-CNN instead of DDN-CVPR17Rain removal · Panning unstable camera (avg. a)PSNR: 28.82 -> 31.11Helped
use SPAC-CNN instead of DDN-CVPR17Rain removal · Fast camera (20–30 km/h; avg. b)PSNR: 30.23 -> 33.19Helped
add F1 (occluded-background feature) (ablation)SPAC-CNN · Clip a1PSNR: 25.28 -> 29.78Helped
add F2 (temporal-consistency feature) (ablation)SPAC-CNN · Clip a1PSNR: 28.87 -> 29.78Helped
add F3 (high-frequency-detail feature) (ablation)SPAC-CNN · Clip a1PSNR: 27.63 -> 29.78Helped
add F1 (occluded-background feature) (ablation)SPAC-CNN · Clip b4PSNR: 28.62 -> 33.79Helped
add F2 (temporal-consistency feature) (ablation)SPAC-CNN · Clip b4PSNR: 31.97 -> 33.79Helped
add F3 (high-frequency-detail feature) (ablation)SPAC-CNN · Clip b4PSNR: 32.99 -> 33.79Helped

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