TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolution

arXiv:2610.14281v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in image super-resolution (SR) by leveraging strong generative priors to enhance perceptual quality. However, for textual content, these priors often produce text hallucinations: non-existent or distorted text, which alter scene semantics and compromise model reliability. While recent methods focus on enhancing text generation, they do so indiscriminately, leaving hallucinations fundamentally unresolved. We argue the core problem is a lack of selective control. Therefore, we reformulate text SR as a selective generation problem: text is resolved only when reliable generation is expected, while other scene content is fully super-resolved. We introduce TGSR (Text-Grounded Super-Resolution), a test-time framework that progressively identifies and suppresses likely hallucinated text regions during generation. To enable this, we train dedicated detectors on a large-scale dataset curated from diverse diffusion-based SR outputs. TGSR consistently improves text fidelity across multiple backbones, increasing recognition precision by up to 17.68 points without degrading perceptual quality, underscoring the value of selective control in generative SR.

Related

• RFMSR: Residual Flow Matching for Image Super-Resolution
• SR-Ground: Image Quality Grounding for Super-Resolved Content
• InfScene-SR: Seamless Super-Resolution of Arbitrarily Large Remote-Sensing Scenes via Variance-Preserving Joint Denoising
• Zero-Shot Video Restoration and Enhancement with Text-to-Image Latent Diffusion Models and Multi-Modal References

Source: arXiv cs.CV | 2026-10-14