PulseAugur
EN
LIVE 07:02:02

DinoLizer model identifies generative inpainting artifacts with 20% higher accuracy

By PulseAugur Editorial · [1 sources] ·

Researchers have developed DinoLizer, a new method for identifying manipulated regions in generative inpainting. This DINOv2-based localizer achieves a 20% higher Intersection over Union score than existing methods by focusing on semantically altered areas. DinoLizer is trained using LORA on transformer blocks and demonstrates robustness against JPEG compression, with its code made publicly available. AI

IMPACT Enhances the detection of AI-generated image manipulations, improving content authenticity verification.

RANK_REASON The cluster describes a new research paper detailing a novel model for image manipulation detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

DinoLizer model identifies generative inpainting artifacts with 20% higher accuracy

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Minh Thong Doi (IMT Nord Europe, CRIStAL), Vincent Itier (IMT Nord Europe, CRIStAL), Jan Butora (CRIStAL), J\'er\'emie Boulanger (CRIStAL), Patrick Bas (CRIStAL) ·

    DinoLizer: Separating VAE and Diffusion Artifacts in Generative Inpainting Localization

    arXiv:2511.20722v2 Announce Type: replace Abstract: We introduce DinoLizer, a DINOv2-based localizer of manipulated areas in generative inpainting. The model is trained to focus on semantically altered regions by treating reconstructed areas outside the inpainted mask as a separa…

RELATED ENTITIES

RELATED TOPICS