AI Paper Atlas

Research map / Image generation / Image restoration

Dynamic Exposure Burst Image Restoration

Woohyeok Kim, Jaesung Rim, Daeyeon Kim, Sunghyun Cho

CVPR 2026 · Image generation › Image restoration · approach: Real-world restoration with unaligned data · 0 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
predict per-frame exposure times with BAENet instead of fixed bracketDEBIR/Burstormer · Simulated test setPSNR: 35.04 -> 35.32Improved
predict per-frame exposure times instead of real-camera exposure bracketingDEBIR · Real-world capturesBRISQUE: 50.66 -> 46.90Improved
use non-uniform instead of uniform exposure times (ablation)DEBIR · Simulated test setPSNR: 35.01 -> 35.32Improved
add preview image input to BAENet (ablation)BAENet · Simulated test setPSNR: 34.80 -> 35.32Improved
add gain input to BAENet (ablation)BAENet · Simulated test setPSNR: 35.21 -> 35.32Improved
add motion magnitude input to BAENet (ablation)BAENet · Simulated test setPSNR: 35.13 -> 35.32Improved
add BAENet warm-up with pseudo-ground-truth exposure times (S2-1) (ablation)DEBIR training · Simulated test setPSNR: 35.16 -> 35.32Improved
add fine-tuning of restoration network (S3) (ablation)DEBIR training · Simulated test setPSNR: 35.01 -> 35.32Improved
use staged training instead of end-to-end training (ablation)DEBIR training · Simulated test setPSNR: 33.60 -> 35.32Improved
use end-to-end finetuning instead of S3 restoration finetuning (ablation)DEBIR training · Simulated test setPSNR: 35.32 -> 35.11Hurt
increase burst size from 2 to 8 (ablation)DEBIR · Simulated test setPSNR: 34.22 -> 36.11Improved
DEBIR vs exposure bracketing as burst size grows (ablation)DEBIR · Simulated test setPSNR: +0.63 dB at n=2, +0.22 at n=8 (34.22 vs 33.59; 36.11 vs 35.89)Mixed

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