Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
This work addresses challenges in generative modeling for layout-to-image tasks, offering incremental improvements in representation and evaluation methods.
The paper tackles the problem of layout-to-image generation by introducing a regional cross-attention module to improve handling of complex textual descriptions, and proposes new metrics for open-vocabulary evaluation, validated through a user study.
Recent advancements in generative models have significantly enhanced their capacity for image generation, enabling a wide range of applications such as image editing, completion and video editing. A specialized area within generative modeling is layout-to-image (L2I) generation, where predefined layouts of objects guide the generative process. In this study, we introduce a novel regional cross-attention module tailored to enrich layout-to-image generation. This module notably improves the representation of layout regions, particularly in scenarios where existing methods struggle with highly complex and detailed textual descriptions. Moreover, while current open-vocabulary L2I methods are trained in an open-set setting, their evaluations often occur in closed-set environments. To bridge this gap, we propose two metrics to assess L2I performance in open-vocabulary scenarios. Additionally, we conduct a comprehensive user study to validate the consistency of these metrics with human preferences.