VideoVerse: How Far is Your T2V Generator from a World Model?
This addresses the need for better evaluation metrics in T2V generation, which is critical for building world models, though it is incremental as it builds upon existing benchmarking efforts.
The authors tackled the problem of insufficient benchmarks for evaluating state-of-the-art Text-to-Video (T2V) models by introducing VideoVerse, a comprehensive benchmark focusing on temporal causality and world knowledge, resulting in a dataset with 300 prompts, 815 events, and 793 binary evaluation questions.
The recent rapid advancement of Text-to-Video (T2V) generation technologies, which are critical to build ``world models'', makes the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models. First, current evaluation dimensions, such as per-frame aesthetic quality and temporal consistency, are no longer able to differentiate state-of-the-art T2V models. Second, event-level temporal causality, which not only distinguishes video from other modalities but also constitutes a crucial component of world models, is severely underexplored in existing benchmarks. Third, existing benchmarks lack a systematic assessment of world knowledge, which are essential capabilities for building world models. To address these issues, we introduce VideoVerse, a comprehensive benchmark that focuses on evaluating whether a T2V model could understand complex temporal causality and world knowledge in the real world. We collect representative videos across diverse domains (e.g., natural landscapes, sports, indoor scenes, science fiction, chemical and physical experiments) and extract their event-level descriptions with inherent temporal causality, which are then rewritten into text-to-video prompts by independent annotators. For each prompt, we design a suite of binary evaluation questions from the perspective of dynamic and static properties, with a total of ten carefully defined evaluation dimensions. In total, our VideoVerse comprises 300 carefully curated prompts, involving 815 events and 793 binary evaluation questions. Consequently, a human preference aligned QA-based evaluation pipeline is developed by using modern vision-language models. Finally, we perform a systematic evaluation of state-of-the-art open-source and closed-source T2V models on VideoVerse, providing in-depth analysis on how far the current T2V generators are from world models.