Local-Global Context-Aware and Structure-Preserving Image Super-Resolution

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Palit, Sanchar, Chaudhuri, Subhasis, Banerjee, Biplab
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914095268102144
author Palit, Sanchar
Chaudhuri, Subhasis
Banerjee, Biplab
author_facet Palit, Sanchar
Chaudhuri, Subhasis
Banerjee, Biplab
contents Diffusion models have recently achieved significant success in various image manipulation tasks, including image super-resolution and perceptual quality enhancement. Pretrained text-to-image models, such as Stable Diffusion, have exhibited strong capabilities in synthesizing realistic image content, which makes them particularly attractive for addressing super-resolution tasks. While some existing approaches leverage these models to achieve state-of-the-art results, they often struggle when applied to diverse and highly degraded images, leading to noise amplification or incorrect content generation. To address these limitations, we propose a contextually precise image super-resolution framework that effectively maintains both local and global pixel relationships through Local-Global Context-Aware Attention, enabling the generation of high-quality images. Furthermore, we propose a distribution- and perceptual-aligned conditioning mechanism in the pixel space to enhance perceptual fidelity. This mechanism captures fine-grained pixel-level representations while progressively preserving and refining structural information, transitioning from local content details to the global structural composition. During inference, our method generates high-quality images that are structurally consistent with the original content, mitigating artifacts and ensuring realistic detail restoration. Extensive experiments on multiple super-resolution benchmarks demonstrate the effectiveness of our approach in producing high-fidelity, perceptually accurate reconstructions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
Palit, Sanchar
Chaudhuri, Subhasis
Banerjee, Biplab
Computer Vision and Pattern Recognition
Diffusion models have recently achieved significant success in various image manipulation tasks, including image super-resolution and perceptual quality enhancement. Pretrained text-to-image models, such as Stable Diffusion, have exhibited strong capabilities in synthesizing realistic image content, which makes them particularly attractive for addressing super-resolution tasks. While some existing approaches leverage these models to achieve state-of-the-art results, they often struggle when applied to diverse and highly degraded images, leading to noise amplification or incorrect content generation. To address these limitations, we propose a contextually precise image super-resolution framework that effectively maintains both local and global pixel relationships through Local-Global Context-Aware Attention, enabling the generation of high-quality images. Furthermore, we propose a distribution- and perceptual-aligned conditioning mechanism in the pixel space to enhance perceptual fidelity. This mechanism captures fine-grained pixel-level representations while progressively preserving and refining structural information, transitioning from local content details to the global structural composition. During inference, our method generates high-quality images that are structurally consistent with the original content, mitigating artifacts and ensuring realistic detail restoration. Extensive experiments on multiple super-resolution benchmarks demonstrate the effectiveness of our approach in producing high-fidelity, perceptually accurate reconstructions.
title Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.13649