AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Unified Framework for Event-Based Frame Interpolation With Ad-Hoc Deblurring in the Wild

Lei Sun, Daniel Gehrig, Christos Sakaridis, Mathias Gehrig, Jingyun Liang, Peng Sun, Zhijie Xu, Kaiwei Wang, Luc Van Gool, Davide Scaramuzza

TPAMI 2024 · Video › Video segmentation and tracking · approach: Video frame interpolation

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 multi-scale connection between image and event branches (ablation)REFID · GoPro blurry frame interpolation (11+1)PSNR: +0.37 dBImproved
add recurrent EVR block (vs non-recurrent) (ablation)REFID · GoPro blurry frame interpolation (11+1)PSNR: +1.75 dBImproved
make EVR block bidirectional (ablation)REFID · GoPro blurry frame interpolation (11+1)PSNR: +0.45 dBImproved
use EVR block instead of ConvLSTM/ConvGRU (ablation)REFID · GoPro blurry frame interpolation (11+1)PSNR: +0.84 dBImproved
add EGACA event-guided channel attention fusion (ablation)REFID · GoPro blurry frame interpolation (11+1)PSNR: +0.31 dBImproved
all components together versus baseline (ablation)REFID · GoPro blurry frame interpolation (11+1)PSNR and SSIM: 33.24 -> 36.12 PSNR; 0.950 -> 0.974 SSIMImproved
add blur consistency loss to brightness increment plus warp loss (ablation)REFID (ssl.) · GoPro self-supervised deblurringPSNR: 7.22 -> 28.88Improved
add warp loss to brightness increment and blur consistency (ablation)REFID (ssl.) · HighREV self-supervised deblurringPSNR: 27.81 -> 30.04Improved
add brightness increment loss to blur and warp losses (ablation)REFID (ssl.) · HighREV self-supervised deblurringPSNR: 28.53 -> 30.04Improved
add brightness increment loss to blur and warp losses (ablation)REFID (ssl.) · GoPro self-supervised deblurringPSNR: 27.72 -> 28.88Improved
add images of warped events (IWE) as input (ablation)REFID (ssl.) · HighREV self-supervised deblurringPSNR: 30.04 -> 30.94Improved
use RobustNorm+ instead of RobustNorm voxel normalization (ablation)REFID (ssl.) · HighREV self-supervised deblurringPSNR: 28.98 -> 30.04Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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