AI Paper Atlas

Research map / Image generation / Image restoration

Face De-Spoofing: Anti-Spoofing via Noise Modeling

Amin Jourabloo, Yaojie Liu, Xiaoming Liu

ECCV 2018 · Image generation › Image restoration · approach: Self-supervised image denoising · 292 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 magnitude loss (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 5.24 -> 1.50Improved
add 0/1 map loss (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 2.34 -> 1.50Improved
add repetitive loss (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.50 -> 1.50No clear effect
add repetitive loss on 1080P cheek-region input (ablation)De-Spoof Net · Oulu-NPU Protocol 1 (1080P cheek region)ACER (%): cannot converge -> 2.92Improved
fuse spoof noise and depth map scores by average instead of using spoof noise alone (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.70 -> 1.50Improved
fuse spoof noise and depth map by average instead of depth map alone (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.67 -> 1.50Improved
use maximum instead of average fusion of spoof noise and depth (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.50 -> 1.72Hurt
add 0/1 map score to fusion of spoof noise and depth (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.50 -> 1.50No clear effect
reduce input resolution from 256x256 to 128x128 (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.50 -> 3.07Hurt
reduce input resolution from 256x256 to 64x64 (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.50 -> 5.27Hurt
blur input with 9x9 Gaussian filter (ablation)De-Spoof Net · Oulu-NPU Protocol 1ACER (%): 1.50 -> 4.89Hurt
train on higher-resolution CASIA-MFSD and test on lower-resolution Replay-Attack versus reverseDe-Spoof Net · Cross test CASIA-MFSD / Replay-AttackHTER (%): 28.5 -> 41.1Mixed

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