ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization

TL;DR

ForgeryVCR is proposed, a framework that incorporates a forensic toolbox to materialize imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning and achieves state-of-the-art (SOTA) performance in both detection and localization tasks, demonstrating superior generalization and robustness with minimal tool redundancy.

Abstract

Existing Multimodal Large Language Models (MLLMs) for image forgery detection and localization predominantly operate under a text-centric Chain-of-Thought (CoT) paradigm. However, forcing these models to textually characterize imperceptible low-level tampering traces inevitably leads to hallucinations, as linguistic modalities are insufficient to capture such fine-grained pixel-level inconsistencies. To overcome this, we propose ForgeryVCR, a framework that incorporates a forensic toolbox to materialize imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning. To enable efficient tool utilization, we introduce a Strategic Tool Learning post-training paradigm, encompassing gain-driven trajectory construction for Supervised Fine-Tuning (SFT) and subsequent Reinforcement Learning (RL) optimization guided by a tool utility reward. This paradigm empowers the MLLM to act as a proactive decision-maker, learning to spontaneously invoke multi-view reasoning paths including local zoom-in for fine-grained inspection and the analysis of invisible inconsistencies in compression history, noise residuals, and frequency domains. Extensive experiments reveal that ForgeryVCR achieves state-of-the-art (SOTA) performance in both detection and localization tasks, demonstrating superior generalization and robustness with minimal tool redundancy. The project page is available at https://youqiwong.github.io/projects/ForgeryVCR/.

Figures (13)

• Figure 1: Motivation. Unlike prior methods limited by semantic bias, ForgeryVCR employs Visual-Centric Reasoning, grounding the verdict in visual evidence rather than vague descriptions.
• Figure 2: Overview of the ForgeryVCR Framework. The top panel depicts the architecture. The training pipeline: (1) Stage 1 uses Gain-Driven Tool Selection and Multi-Trajectories Synthesis to construct diverse reasoning paths; (2) Stage 2 optimizes the policy via GRPO with Tool-Utility Reward to foster strategic tool usage. The right panel shows the reasoning chain invoking tools to expose subtle artifacts for precise localization, guiding SAM2 to generate the fine-grained mask.
• Figure 3: Pipeline of Visual-Centric Trajectory Construction.
• Figure 4: Evolution of training dynamics during the RL stage.
• Figure 5: Comparison of specific tool usage ratios between SFT and RL stages.