Rethinking Super-Resolution as Text-Guided Details Generation

TL;DR

This paper introduces a novel text-guided super-resolution framework that leverages multi-modal fusion to generate high-resolution images with details aligned to textual descriptions, improving realism and semantic accuracy.

Contribution

It proposes a new text-guided super-resolution approach that incorporates text-image fusion to enhance detail generation beyond traditional image-only methods.

Findings

Effective generation of semantically aligned high-resolution images

Improved visual quality with text-guided detail enhancement

Demonstrated superiority over existing super-resolution techniques

Abstract

Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However, the image-level information is insufficient to predict adequate details and photo-realistic visual quality facing large upscaling factors (x8, x16). In this paper, we propose a new perspective that regards the SISR as a semantic image detail enhancement problem to generate semantically reasonable HR image that are faithful to the ground truth. To enhance the semantic accuracy and the visual quality of the reconstructed image, we explore the multi-modal fusion learning in SISR by proposing a Text-Guided Super-Resolution (TGSR) framework, which can effectively utilize the information from the text and image modalities. Different from existing methods, the proposed TGSR could generate HR image details that match the text descriptions through a coarse-to-fine process. Extensive experiments and ablation studies demonstrate the effect of the TGSR, which exploits the text reference to recover realistic images.