Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generation

TL;DR

This paper introduces Flow of Truth, a proactive temporal forensic framework for image-to-video generation that tracks pixel motion over time to detect forgeries.

Contribution

It presents a novel approach redefining video generation as pixel motion, with a learnable forensic template and flow module for robust temporal tracing.

Findings

Generalizes across various I2V models

Significantly improves temporal forensic accuracy

Decouples motion from content for better tracing

Abstract

The rapid rise of image-to-video (I2V) generation enables realistic videos to be created from a single image but also brings new forensic demands. Unlike static images, I2V content evolves over time, requiring forensics to move beyond 2D pixel-level tampering localization toward tracing how pixels flow and transform throughout the video. As frames progress, embedded traces drift and deform, making traditional spatial forensics ineffective. To address this unexplored dimension, we present **Flow of Truth**, the first proactive framework focusing on temporal forensics in I2V generation. A key challenge lies in discovering a forensic signature that can evolve consistently with the generation process, which is inherently a creative transformation rather than a deterministic reconstruction. Despite this intrinsic difficulty, we innovatively redefine video generation as *the motion of pixels through time rather than the synthesis of frames*. Building on this view, we propose a learnable forensic template that follows pixel motion and a template-guided flow module that decouples motion from image content, enabling robust temporal tracing. Experiments show that Flow of Truth generalizes across commercial and open-source I2V models, substantially improving temporal forensics performance.