AI Paper Atlas

Research map / Video / Video segmentation and tracking

"UniINR: Event-guided Unified Rolling Shutter Correction, Deblurring, and Interpolation"

Yunfan Lu, Guoqiang Liang, Yusheng Wang, Lin Wang, Hui Xiong

ECCV 2024 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 8 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
replace sinusoid with learned exposure time embedding (ablation)UniINR · Gev-Blur grayPSNR: 32.46 -> 33.12 (1x); +1.11 totalImproved
add blur-frame integral loss L_b (ablation)UniINR · Gev-Blur grayPSNR: +0.060No clear effect
use concatenation or multiplication instead of addition for time embedding (ablation)UniINR · Gev-RS gray 9xPSNR: 30.54 -> 30.77Improved
use one-stage unified INR instead of two-stage deblur then RS-correctUniINR vs EvUnRoll · Gev-Blur 1x colorPSNR: 26.18 -> 30.35Improved
unified model instead of cascading EvUnRoll + TimeLensRS correction + deblur + VFI · Gev-Blur 3x colorPSNR: 21.86 -> 28.36Improved
increase interpolation from 1x to 31x with single shared encoderUniINR · inference timetotal time (ms): 30.8 ms -> 86.9 ms for 31xImproved
apply UniINR for RS correction only on Fastec-OrigUniINR · Fastec-OrigPSNR: 32.41 -> 33.91Improved
increase interpolation from 3x to 5x for color framesUniINR · Gev-Blur colorPSNR: 28.36 -> 28.41No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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