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

arXiv cs.CV / 4/17/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that image-to-video (I2V) forensics must go beyond static, 2D pixel tampering detection because evidence changes dynamically as frames evolve.
It proposes “Flow of Truth,” a proactive temporal forensics framework that traces how pixels move and transform over time, treating I2V generation as pixel flow through time rather than frame-by-frame reconstruction.
The method introduces a learnable forensic template that evolves consistently with the generation process and a template-guided flow module that separates motion from image content.
Experiments indicate the approach generalizes across both commercial and open-source I2V models, delivering substantially better temporal forensics performance than prior approaches.

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.