AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Who Controls the Authorization? Invertible Networks for Copyright Protection in Text-to-Image Synthesis

Baoyue Hu, Yang Wei, Junhao Xiao, Wendong Huang, Xiuli Bi, Bin Xiao

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 1 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 contrastive learning-based adversarial loss Ladvc (ablation)Ours · VGGFace2 (20 identities)FID: 214.22 -> 324.11Improved
add contrastive learning-based adversarial loss Ladvc (ablation)Ours · VGGFace2 (20 identities)PSNR: 36.1336 -> 30.7634Hurt
add DWT frequency-domain processing (ablation)Ours · VGGFace2 (20 identities)FID: 317.35 -> 324.11Improved
add DWT frequency-domain processing (ablation)Ours · VGGFace2 (20 identities)PSNR: 28.9580 -> 30.7634Improved
add compound coupling module (ablation)Ours · VGGFace2 (20 identities)FID: 314.10 -> 324.11Improved
apply JPEG compression purification to copyrighted imagesOurs · VGGFace2FID: 300.35 -> 300.59No clear effect
apply super-resolution purification to copyrighted imagesOurs · VGGFace2FID: 300.35 -> 306.11No clear effect
apply Gaussian filtering purification to copyrighted imagesOurs · VGGFace2FID: 300.35 -> 175.76Hurt
use unseen prompt (dslr portrait) instead of training promptOurs · VGGFace2FID: 300.35 -> 314.71Improved
use unseen prompt instead of training promptMetaCloak · VGGFace2FID: 193.17 -> 154.89Hurt
use Ours instead of ASPL on facial identity disruptionOurs · VGGFace2ISM: 0.3208 -> 0.4611Hurt
use Ours instead of Wm-AdvDMOurs · VGGFace2FID: 160.12 -> 300.35Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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