AI Paper Atlas

Research map / Image generation / Image restoration

Localization of Deep Inpainting Using High-Pass Fully Convolutional Network

Haodong Li, Jiwu Huang

ICCV 2019 · Image generation › Image restoration · approach: Dehazing and deraining · 188 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
use transpose convolution instead of bilinear resizing for up-sampling (ablation)high-pass FCN · Synthetic inpainted ImageNet (QF=75, ablation)F1-score (%): 89.13 -> 91.53Improved
use focal loss instead of standard cross entropy (ablation)high-pass FCN · Synthetic inpainted ImageNet (QF=75, ablation)F1-score (%): 91.17 -> 91.53Improved
use focal loss instead of weighted cross entropy (ablation)high-pass FCN · Synthetic inpainted ImageNet (QF=75, ablation)F1-score (%): 90.69 -> 91.53Improved
use weighted cross entropy instead of focal loss (ablation)high-pass FCN · Synthetic inpainted ImageNet (QF=75, ablation)Recall (%): 89.84 -> 90.54Mixed
initialize pre-filter with 1st-order derivative high-pass filters rather than higher-order ones (ablation)high-pass FCN · Synthetic inpainted ImageNet (QF=75, ablation)F1-score (%)Improved
add high-pass pre-filtering module (ablation)high-pass FCN · Synthetic inpainted ImageNet (QF=75, ablation)F1-score (%)Improved
add Gaussian noise at SNR 40 dB instead of 50 dBProposed · Noisy JPEG images, QF=75F1-score (%): 91.49 -> 91.18No clear effect
add Gaussian noise at SNR 30 dB instead of 50 dBProposed · Noisy JPEG images, QF=75F1-score (%): 91.49 -> 77.00Hurt
lower JPEG quality factor from 96 to 75Proposed · Synthetic inpainted ImageNetF1-score (%): 97.28 -> 91.53Hurt
Proposed instead of MFCN splicing localizerMFCN · Synthetic inpainted ImageNet (QF=75)F1-score (%): 45.01 -> 91.53Improved
Proposed instead of best Patch-CNN (b=64)Patch-CNN · Synthetic inpainted ImageNet (QF=75)F1-score (%): 75.15 -> 91.53Improved
increase Patch-CNN window size from 16 to 32 then 64Patch-CNN · Synthetic inpainted ImageNet (QF=96)F1-score (%): 78.49 -> 82.90 -> 72.80Mixed

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