AI Paper Atlas

Research map / Detection and segmentation / CNN features

Real-World Deep Local Motion Deblurring

Haoying Li, Ziran Zhang, Tingting Jiang, Peng Luo, Huajun Feng, Zhihai Xu

AAAI 2023 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 33 citations (OpenAlex)

This paper tried a common change: Pretrained initialization

Initialize with pretrained MIMO-Unet weights · ReLoBlur test · Weighted PSNR: 28.10 -> 28.32 Improved

What 86 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
Use LBAG instead of MIMO-UnetReLoBlur deblurring · ReLoBlur testWeighted PSNR: 27.95 -> 28.25Improved
Add pretrained MIMO-Unet backbone initializationLBAG · ReLoBlur testWeighted PSNR: 28.25 -> 28.32Improved
Add gate blocks that localize blur and gate reconstruction (ablation)LBAG+ · ReLoBlur testWeighted PSNR: 27.88 -> 28.32Improved
Use Blur-Aware Patch Cropping (ablation)LBAG+ · ReLoBlur testWeighted PSNR: 28.17 -> 28.32Improved
Add SSIM loss term (ablation)LBAG+ · ReLoBlur testWeighted SSIM: 0.8639 -> 0.8734Improved
Initialize with pretrained MIMO-Unet weights (ablation)LBAG · ReLoBlur testWeighted PSNR: 28.10 -> 28.32Improved
Train LBAG+ on real ReLoBlur data rather than synthetic local-blur dataLBAG+ · ReLoBlur testWeighted PSNR: 27.42 -> 28.32Improved

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