AI Paper Atlas

Research map / Video / Video segmentation and tracking

CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring

Taewoo Kim, Hoonhee Cho, Kuk-Jin Yoon

ECCV 2024 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 22 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 the CRIFE module (ablation)CMTA baseline (no ECITFA) · GoProPSNR: 34.65 -> 35.00Improved
add the ECITFA module (ablation)CMTA baseline (no CRIFE) · GoProPSNR: 34.65 -> 36.34Improved
add CRIFE to the model with ECITFA (ablation)CMTA · GoProPSNR: 36.34 -> 36.55Improved
add pixel-wise dynamic filters in alignment (ablation)ECITFA · GoProPSNR: 36.18 -> 36.55Improved
use cross-attention instead of ResBlocks for feature aggregation in alignment (ablation)ECITFA · GoProPSNR: 36.29 -> 36.55Improved
use cascaded temporal feature alignment (ablation)ECITFA · GoProPSNR: 36.08 -> 36.55Improved
concatenate RGB and event features for the query in CRIFE (ablation)CRIFE · GoProPSNR: 36.04 -> 36.55Improved
use recurrent structure in CRIFE (ablation)CRIFE · GoProPSNR: 35.99 -> 36.55Improved
increase input frames from 5 to 7CMTA · GoProPSNR: 36.55 -> 36.78Improved
add event guidance over best frame-based video deblurringShift-Net vs CMTA-5 · GoProPSNR: 35.49 -> 36.55Improved

Later papers that compared with this method

3 later accepted papers report CMTA-7 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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