AI Paper Atlas

Research map / Video / Video segmentation and tracking

Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction

Delin Qu, Yizhen Lao, Zhigang Wang, Dong Wang, Bin Zhao, Xuelong Li

ICCV 2023 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 11 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
add RSAdaCof alignment/aggregation warping (ablation)RSA2-Net · Fastec-RSPSNR: 28.70 -> 29.49Improved
add Multi-QRS correction field as network input (ablation)RSA2-Net · Carla-RS (no mask)PSNR: 30.92 -> 32.01Improved
use 3D-Transformer instead of 3D-UNet encoder (ablation)RSA2-Net · BS-RSCPSNR: 33.41 -> 33.50No clear effect
use 3D-Transformer instead of 3D-UNet encoder (ablation)RSA2-Net · Fastec-RSPSNR: 28.51 -> 29.49Improved
increase number of input frames from 3 to 5 (ablation)full model · Carla-RS (no mask)PSNR: 29.81 -> 32.01Improved
use quadratic motion model instead of linear model (ablation)QRS motion solver · Fastec-RS and BS-RSCPSNRImproved
QRS solver and RSA2-Net combined instead of either alone (ablation)full model · Fastec-RS and BS-RSCPSNRImproved
test on ACC (variable motion) instead of BS-RSCproposed method vs baselines · BS-RSC vs ACCPSNR: 33.50 -> 33.36No clear effect

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