Face Consistency Benchmark for GenAI Video

TL;DR

This paper presents the Face Consistency Benchmark (FCB), a standardized evaluation framework designed to measure and compare character consistency in AI-generated videos, addressing a key challenge in AI video synthesis.

Contribution

The paper introduces the Face Consistency Benchmark (FCB), providing standardized metrics to evaluate and compare character consistency in AI-generated videos, highlighting current gaps and guiding future improvements.

Findings

Current models struggle with character consistency in AI videos.

FCB provides a standardized way to evaluate consistency.

Benchmark reveals significant gaps in existing solutions.

Abstract

Video generation driven by artificial intelligence has advanced significantly, enabling the creation of dynamic and realistic content. However, maintaining character consistency across video sequences remains a major challenge, with current models struggling to ensure coherence in appearance and attributes. This paper introduces the Face Consistency Benchmark (FCB), a framework for evaluating and comparing the consistency of characters in AI-generated videos. By providing standardized metrics, the benchmark highlights gaps in existing solutions and promotes the development of more reliable approaches. This work represents a crucial step toward improving character consistency in AI video generation technologies.