AI Paper Atlas

Research map / Video / Video segmentation and tracking

Hybrid Neural Fusion for Full-Frame Video Stabilization

Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang

ICCV 2021 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 71 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 in hybrid space instead of feature space (ablation)CNN-based fusion · Fusion ablation (940 synthetic test videos)PSNR: 27.187 -> 27.868Improved
fuse in hybrid space instead of image space (ablation)CNN-based fusion · Fusion ablation (940 synthetic test videos)PSNR: 26.692 -> 27.868Improved
fuse in hybrid space instead of feature space (ablation)CNN-based fusion · Fusion ablation (940 synthetic test videos)LPIPS: 0.092 -> 0.073Improved
use CNN-based fusion function instead of mean in hybrid space (ablation)hybrid-space fusion · Fusion ablation (940 synthetic test videos)PSNR: 27.013 -> 27.868Improved
use CNN-based fusion function instead of argmax in hybrid space (ablation)hybrid-space fusion · Fusion ablation (940 synthetic test videos)PSNR: 27.519 -> 27.868Improved
use CNN-based fusion instead of argmax in image space (ablation)image-space fusion · Fusion ablation (940 synthetic test videos)SSIM: 0.928 -> 0.895Hurt
add flow-error weighting instead of mean in image space (ablation)image-space fusion · Fusion ablation (940 synthetic test videos)PSNR: 24.618 -> 25.363Improved
combine proposed method with Bundle smoothingBundle · Selfie datasetaccumulated optical flow: 0.84 -> 0.70Improved
combine proposed method with Yu and Ramamoorthi smoothingYu and Ramamoorthi · Selfie datasetcropping ratio: 0.78 -> 1.00Improved
combine proposed method with Bundle smoothingBundle · Selfie datasetstability score: 0.85 -> 0.85No clear effect
use hybrid fusion for view synthesis instead of FVSFVS · Tanks and Temples TruckPSNR: 22.21 -> 23.25Improved
full-frame fusion instead of cropping-based stabilizersAdobe Premiere Pro · NUS datasetcropping ratio: 0.74 -> 1.00Improved

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