atlas

Research map / Video / Video segmentation and tracking

Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring

AAAI 2022 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 53 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 RNN-MBP instead of HINetGOPRO deblurring · GOPROPSNR: 32.71 -> 33.32Helped
Train RNN-MBP on RBVD rather than GOPRORNN-MBP · RBVDPSNR: 22.826 -> 26.555Helped
Add multi-scale bidirectional propagation to the basic RNN (ablation)Baseline video deblurring model · GOPROPSNR: 31.443 -> 32.087Helped
Add SpyNet alignment to the basic RNN (ablation)Baseline video deblurring model · GOPROPSNR: 31.443 -> 30.689Hurt
Add deformable alignment layers to the basic RNN (ablation)Baseline video deblurring model · GOPROPSNR: 31.443 -> 26.234Hurt
Add Target Frame Re-constructor to Baseline+MBP (ablation)Baseline+MBP · GOPROPSNR: 32.087 -> 33.319Helped
Add Target Frame Re-constructor to Baseline+MBP (ablation)Baseline+MBP · GOPROSSIM: 0.9524 -> 0.9627Helped

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