AI Paper Atlas

Research map / Image generation / Image restoration

NOWA: Null-space Optical Watermark for Invisible Capture Fingerprinting and Tamper Localization

Edwin Vargas, Jhon Lopez, Henry Arguello, Ashok Veeraraghavan

CVPR 2026 · Image generation › Image restoration · approach: Reflection removal · 0 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
feed null-space projection to the detector instead of the protected image (ablation)NOWA detector · Tamper localization (COCO)F1: 0.75 -> near-perfect (F1~0.75, AUC~0.82, IoU~0.69 with image input)Improved
add a learned phase mask (vs no mask) (ablation)NOWA · Tamper localizationF1: F1=0.89, IoU=0.81 without maskImproved
embed optical null-space watermark vs EditGuardNOWA · Tamper localization, Stable Diffusion editsF1: 0.966 -> 0.993Improved
embed optical null-space watermark vs EditGuardNOWA · Tamper localization, SDXL editsF1: 0.965 -> 0.929Hurt
embed optical null-space watermark vs EditGuardNOWA · Tamper localization, Lama editsIoU: 0.934 -> 0.933No clear effect
NOWA vs EditGuard under JPEG Q=70NOWA · Tamper localization under JPEGF1: 0.552 -> 0.885Improved
NOWA vs EditGuard under Gaussian noise sigma=5NOWA · Tamper localization under noiseF1: 0.871 -> 0.982Improved
NOWA vs purely digital HiFi-Net under degradationNOWA · Tamper localization under degradationF1: 0.156 -> 0.982 (sigma=5)Improved
NOWA vs purely digital detectors (MVSS-Net, OSN, PSCC-Net)NOWA · Tamper localization under AIGC editsF1: F1<0.2 for digital detectors -> 0.993Improved
attacker imitates camera outputs with generative modelNOWA verification · Adversarial robustness, Attack 1F1: detection F1 0.901Improved
attacker imitates protected images with generative modelNOWA verification · Adversarial robustness, Attack 2F1: detection F1 0.913Improved
attacker estimates PSF by blind deconvolutionNOWA verification · Adversarial robustness, Attack 3F1: detection F1 0.946Improved

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