AI Paper Atlas

Research map / Video / Video segmentation and tracking

EVDI++: Event-Based Video Deblurring and Interpolation via Self-Supervised Learning

Chi Zhang, Xiang Zhang, Chenxu Jiang, Gui-Song Xia, Yu Lei

TPAMI 2026 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 3 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 blurry-event loss L_B-E to the sharp-blurry loss alone (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 28.84 -> 30.04Improved
add blurry-event loss L_B-E to L_S-B plus L_B-B (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 31.57 -> 32.05Improved
add blurry-event loss L_B-E to blurry-blurry loss alone (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 31.39 -> 12.72Hurt
add sharp-blurry loss L_S-B for brightness consistency (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 12.72 -> 32.05Improved
add sharp-blurry loss L_S-B to blurry-event loss alone (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 10.47 -> 30.04Improved
add blurry-blurry loss L_B-B to sharp-blurry loss alone (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 28.84 -> 31.57Improved
add sharp-blurry loss L_S-B to blurry-blurry loss alone (ablation)EVDI++ self-supervised losses · ColorDVS-Real motion deblurringPSNR: 31.39 -> 31.57Improved
add all three losses versus L_S-B alone on frame interpolation (ablation)EVDI++ self-supervised losses · ColorDVS-Real frame interpolationPSNR: 31.78 -> 32.83Improved
upgrade EVDI to EVDI++ (LDR, APF, new losses)EVDI · ColorDVS-Real motion deblurring (single frame)PSNR: 26.94 -> 32.37Improved
replace learned fusion network with parameter-free APF and drop L_S-EEVDI · REDS training timeseconds per epoch: 5760 -> 360Improved
scale up EVDI++ to the Large modelEVDI++ · BS-ERGB 3-SKIPPSNR: 25.43 -> 26.53Improved
retrain baselines on the target training setsRED-Net / EFNet · ColorDVS-Real motion deblurring (single frame)PSNR: 20.92 -> 34.86Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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