AI Paper Atlas

Research map / Image generation / Image restoration

Extreme-Quality Computational Imaging via Degradation Framework

Shiqi Chen, Huajun Feng, Keming Gao, Zhihai Xu, Yueting Chen

ICCV 2021 · Image generation › Image restoration · approach: Reflection removal · 30 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 estimated degradation kernels from the framework instead of Zemax PSFs (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 33.52 -> 35.93Improved
add unprocess and process operations (energy-domain degradation) (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 35.11 -> 35.93Improved
add optical geometric priors (PSF size and symmetry constraints) (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 33.96 -> 35.93Improved
add FOV Encoder (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 34.69 -> 35.93Improved
add Deformable Decoder (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 35.34 -> 35.93Improved
add KPN Block with dilated kernels (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 35.26 -> 35.93Improved
add optical geometric priors (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)LPIPS: 0.2285 -> 0.1223Improved
add estimated degradation kernels instead of Zemax PSFs (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)LPIPS: 0.2749 -> 0.1223Improved
add FOV Encoder (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)LPIPS: 0.1622 -> 0.1223Improved
add Deformable Decoder (ablation)FOV-KPN with degradation framework · Synthetic test set (DIV2K 50 images, degradation framework)LPIPS: 0.1245 -> 0.1223No clear effect
use FOV-KPN instead of KPN (k=19)KPN · Synthetic test set (DIV2K 50 images, degradation framework)PSNR: 35.62 -> 35.93Improved
use FOV-KPN instead of KPN (k=19)KPN · Synthetic test set (DIV2K 50 images, degradation framework)NIQE: 1.9759 -> 2.0578Hurt

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