TempViz: On the Evaluation of Temporal Knowledge in Text-to-Image Models

TL;DR

This paper introduces TempViz, a new dataset for evaluating how well text-to-image models understand and generate images with temporal context, revealing current models' limited temporal competence and the inadequacy of automated evaluation methods.

Contribution

The paper presents TempViz, the first comprehensive dataset for assessing temporal knowledge in T2I models, and analyzes their performance and evaluation challenges.

Findings

Models show weak temporal understanding, with no exceeding 75% accuracy.

Existing automated evaluation methods are unreliable for temporal assessment.

Human evaluation reveals significant gaps in temporal competence of current T2I models.

Abstract

Time alters the visual appearance of entities in our world, like objects, places, and animals. Thus, for accurately generating contextually-relevant images, knowledge and reasoning about time can be crucial (e.g., for generating a landscape in spring vs. in winter). Yet, although substantial work exists on understanding and improving temporal knowledge in natural language processing, research on how temporal phenomena appear and are handled in text-to-image (T2I) models remains scarce. We address this gap with TempViz, the first data set to holistically evaluate temporal knowledge in image generation, consisting of 7.9k prompts and more than 600 reference images. Using TempViz, we study the capabilities of five T2I models across five temporal knowledge categories. Human evaluation shows that temporal competence is generally weak, with no model exceeding 75% accuracy across categories. Towards larger-scale studies, we also examine automated evaluation methods, comparing several established approaches against human judgments. However, none of these approaches provides a reliable assessment of temporal cues - further indicating the pressing need for future research on temporal knowledge in T2I.