SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Chen, Abdolshah, Majid, Shevchenko, Violetta, Li, Hongdong, Xu, Chang, Purkait, Pulak
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912670659117056
author Chen, Chen
Abdolshah, Majid
Shevchenko, Violetta
Li, Hongdong
Xu, Chang
Purkait, Pulak
author_facet Chen, Chen
Abdolshah, Majid
Shevchenko, Violetta
Li, Hongdong
Xu, Chang
Purkait, Pulak
contents Existing diffusion-based super-resolution approaches often exhibit semantic ambiguities due to inaccuracies and incompleteness in their text conditioning, coupled with the inherent tendency for cross-attention to divert towards irrelevant pixels. These limitations can lead to semantic misalignment and hallucinated details in the generated high-resolution outputs. To address these, we propose a novel, plug-and-play spatially re-focused super-resolution (SRSR) framework that consists of two core components: first, we introduce Spatially Re-focused Cross-Attention (SRCA), which refines text conditioning at inference time by applying visually-grounded segmentation masks to guide cross-attention. Second, we introduce a Spatially Targeted Classifier-Free Guidance (STCFG) mechanism that selectively bypasses text influences on ungrounded pixels to prevent hallucinations. Extensive experiments on both synthetic and real-world datasets demonstrate that SRSR consistently outperforms seven state-of-the-art baselines in standard fidelity metrics (PSNR and SSIM) across all datasets, and in perceptual quality measures (LPIPS and DISTS) on two real-world benchmarks, underscoring its effectiveness in achieving both high semantic fidelity and perceptual quality in super-resolution.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22534
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
Chen, Chen
Abdolshah, Majid
Shevchenko, Violetta
Li, Hongdong
Xu, Chang
Purkait, Pulak
Computer Vision and Pattern Recognition
Existing diffusion-based super-resolution approaches often exhibit semantic ambiguities due to inaccuracies and incompleteness in their text conditioning, coupled with the inherent tendency for cross-attention to divert towards irrelevant pixels. These limitations can lead to semantic misalignment and hallucinated details in the generated high-resolution outputs. To address these, we propose a novel, plug-and-play spatially re-focused super-resolution (SRSR) framework that consists of two core components: first, we introduce Spatially Re-focused Cross-Attention (SRCA), which refines text conditioning at inference time by applying visually-grounded segmentation masks to guide cross-attention. Second, we introduce a Spatially Targeted Classifier-Free Guidance (STCFG) mechanism that selectively bypasses text influences on ungrounded pixels to prevent hallucinations. Extensive experiments on both synthetic and real-world datasets demonstrate that SRSR consistently outperforms seven state-of-the-art baselines in standard fidelity metrics (PSNR and SSIM) across all datasets, and in perceptual quality measures (LPIPS and DISTS) on two real-world benchmarks, underscoring its effectiveness in achieving both high semantic fidelity and perceptual quality in super-resolution.
title SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22534