OrienText: Surface Oriented Textual Image Generation

TL;DR

OrienText is a novel diffusion-based method that improves text placement and orientation accuracy on complex surfaces in images, enhancing applications in e-commerce and advertising.

Contribution

It introduces the use of region-specific surface normals as conditional input to guide text placement in diffusion models, addressing a key challenge in text-to-image generation.

Findings

Effective text rendering on complex surfaces demonstrated

Outperforms existing textual image generation methods

Improves text orientation accuracy in generated images

Abstract

Textual content in images is crucial in e-commerce sectors, particularly in marketing campaigns, product imaging, advertising, and the entertainment industry. Current text-to-image (T2I) generation diffusion models, though proficient at producing high-quality images, often struggle to incorporate text accurately onto complex surfaces with varied perspectives, such as angled views of architectural elements like buildings, banners, or walls. In this paper, we introduce the Surface Oriented Textual Image Generation (OrienText) method, which leverages region-specific surface normals as conditional input to T2I generation diffusion model. Our approach ensures accurate rendering and correct orientation of the text within the image context. We demonstrate the effectiveness of the OrienText method on a self-curated dataset of images and compare it against the existing textual image generation methods.