What question did this study set out to answer?

The aim is to enhance night-time image quality assessment by effectively combining global and local distortion perceptions.

May 25, 2026Scientific Reports0 citationsOpen Access

HCA-Mamba: A Hierarchical Cross-Attention Framework for Night-Time Image Quality Assessment

HCA-Mamba: a hierarchical cross-attention framework combining Vision Mamba and CNN for night-time image quality assessment

View Full Paper

Authors

TZTianqi Zhang WDWu Dong LLLikun Lu

Discussion

Member takes

Overview

Randomized trial assesses night-time image quality through a hybrid framework, suggesting improved accuracy and efficiency.

Key Points

The aim is to enhance night-time image quality assessment by effectively combining global and local distortion perceptions.
Proposed HCA-Mamba framework combines Vision Mamba for global context modeling and CNN for local distortion extraction.
Utilized a multi-scale distortion extractor to compact local degradation cues into distortion-aware tokens.
Implemented a local distortion injection module for gated cross-attention across network depths.
Demonstrated improved performance on NNID and EHNQ benchmarks with effective generalization on NPHD.
Ablation studies confirmed that the multi-scale distortion extractor and local distortion injection module significantly enhanced sensitivity to night-time distortions.

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a13e8520e02ee3982d32fca https://doi.org/10.1038/s41598-026-54065-3

Ask AI

Helpful

Bookmark

View Full Paper

May 25, 2026Scientific Reports0 citationsOpen Access

HCA-Mamba: A Hierarchical Cross-Attention Framework for Night-Time Image Quality Assessment

HCA-Mamba: a hierarchical cross-attention framework combining Vision Mamba and CNN for night-time image quality assessment

View Full Paper

Authors

TZTianqi Zhang WDWu Dong LLLikun Lu

Discussion

Member takes

Overview

Randomized trial assesses night-time image quality through a hybrid framework, suggesting improved accuracy and efficiency.

Key Points

The aim is to enhance night-time image quality assessment by effectively combining global and local distortion perceptions.
Proposed HCA-Mamba framework combines Vision Mamba for global context modeling and CNN for local distortion extraction.
Utilized a multi-scale distortion extractor to compact local degradation cues into distortion-aware tokens.
Implemented a local distortion injection module for gated cross-attention across network depths.
Demonstrated improved performance on NNID and EHNQ benchmarks with effective generalization on NPHD.
Ablation studies confirmed that the multi-scale distortion extractor and local distortion injection module significantly enhanced sensitivity to night-time distortions.

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a13e8520e02ee3982d32fca https://doi.org/10.1038/s41598-026-54065-3

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Ask AI

Helpful

Bookmark

View Full Paper