AI Paper Atlas

Research map / Video / Video segmentation and tracking

Event-Adapted Video Super-Resolution

Zeyu Xiao, Dachun Kai, Yueyi Zhang, Zheng-Jun Zha, Xiaoyan Sun, Zhiwei Xiong

ECCV 2024 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 29 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 EATER (EAA and EAF units) to a frame-only VSR network via parameter-efficient tuningEDVR · CED x4 event-based VSR (average)PSNR (dB): 33.37 -> 33.69Improved
add EATER to BasicVSR++BasicVSR++ · CED x4 event-based VSR (average)PSNR (dB): 32.41 -> 33.55Improved
add EATER to BasicVSRBasicVSR · CED x4 event-based VSR (average)PSNR (dB): 32.75 -> 32.92Improved
use both EAA and EAF units rather than either alone (ablation)EDVR with EATER · CED x4 (EDVR)PSNR (dB): 33.47 -> 33.69Improved
use EAA unit instead of simple concat and conv (ablation)EDVR with EATER · CED x4 (EDVR)PSNR (dB): 33.49 -> 33.69Improved
keep cascading structure in EAA unit (ablation)EDVR with EATER · CED x4 (EDVR)PSNR (dB): 33.62 -> 33.69Improved
use three-scale EAF with cross-scale interaction (ablation)EDVR with EATER · CED x4 (EDVR)PSNR (dB): 33.55 -> 33.69Improved
cross-scale interaction in EAF on BasicVSR (ablation)BasicVSR with EATER · CED x4 (BasicVSR)PSNR (dB): 32.92 -> 32.92No clear effect
use parameter-efficient tuning instead of full fine-tuning (ablation)EDVR · CED x4 (EDVR)PSNR (dB): 33.67 -> 33.69Improved
use parameter-efficient tuning instead of full fine-tuning on training cost (ablation)EDVR · CED x4 (EDVR)training iterations: ~100k -> ~15kImproved

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