AI Paper Atlas

Research map / Image generation / Image restoration

Learning to Deblur Face Images via Sketch Synthesis

Songnan Lin, Jiawei Zhang, Jinshan Pan, Yicun Liu, Yongtian Wang, Jing Chen, Jimmy Ren

AAAI 2020 · Image generation › Image restoration · approach: Image deblurring · 26 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 sketch constraints (sketch synthesis supervision) to the network (ablation)face deblurring network · synthetic face test set (Table 2)PSNR: 23.85 -> 28.57Improved
supervise with face sketches instead of L0-smoothing local structures (ablation)face deblurring network · synthetic face test set (Table 2)PSNR: 27.68 -> 28.57Improved
add explicit kernel estimation and restoration pipeline instead of naive end-to-end (ablation)face deblurring network · synthetic face test set (Table 2)PSNR: 25.72 -> 28.57Improved
estimate kernel in gradient space instead of intensity space (ablation)face deblurring network · synthetic face test set (Table 2)PSNR: 27.37 -> 28.57Improved
feed synthesized sketch into the de-artifact network (ablation)face deblurring network · synthetic face test set (Table 2)PSNR: 28.13 -> 28.57Improved
sketch-based method vs Tao (2018) end-to-end CNNface deblurring · HelenPSNR: 24.89 -> 26.12Improved

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