Venus-DeFakerOne: Unified Fake Image Detection & Localization

TL;DR

DeFakerOne is a unified foundation model that advances fake image detection and localization across diverse forgery scenarios, outperforming existing methods and demonstrating robustness and scalability.

Contribution

It introduces a data-centric, unified model integrating InternVL2 and SAM2 for joint detection and localization, addressing cross-domain artifacts transfer and interference.

Findings

Achieves state-of-the-art performance on 39 detection benchmarks.

Outperforms baselines in forgery localization on 9 benchmarks.

Shows robustness against real-world perturbations and advanced generators.

Abstract

In recent years, the rapid evolution of generative AI has fundamentally reshaped the paradigm of image forgery, breaking the traditional boundaries between document editing, natural image manipulation, DeepFake generation, and full-image AIGC synthesis. Despite this shift toward unified forgery generation, existing research in Fake Image Detection and Localization (FIDL) remains fragmented. This creates a mismatch between increasingly unified forgery generation mechanisms and the domain-specific detection paradigm. Bridging this mismatch poses two key challenges for FIDL: understanding cross-domain artifacts transfer and interference, and building a high-capacity unified foundation model for joint detection and localization. To address these challenges, we propose DeFakerOne, a data-centric, unified FIDL foundation model integrating InternVL2 and SAM2. DeFakerOne enables simultaneous image-level detection and pixel-level forgery localization across diverse scenarios. Extensive experiments demonstrate that DeFakerOne achieves state-of-the-art performance, outperforming baselines on 39 forgery detection benchmarks and 9 localization benchmarks. Furthermore, the model exhibits superior robustness against real-world perturbations and state-of-the-art generators such as GPT-Image-2. Finally, we provide a systematic analysis of data scaling laws, cross-domain artifacts transfer-interference patterns, the necessity of fine-grained supervision, and the original resolution artifacts preservation, highlighting the design principles for scalable, robust, and unified FIDL.