Light-Guided and Cross-Fusion U-Net for Anti-Illumination Image Super-Resolution

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 12; pp. 8436 - 8449
• Main Authors: Cheng, Deqiang, Chen, Liangliang, Lv, Chen, Guo, Lin, Kou, Qiqi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: anti-illumination; cross-fusion; Estimation; Illuminance; Illumination; Image enhancement; Image reconstruction; Image resolution; Image super-resolution; intensity estimation; Interference; Light; Lighting; low-light image; Luminous intensity; Performance degradation; Photodegradation; Robustness; Superresolution; Visual effects
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2022.3194169

The learning-based methods for single image super- resolution (SISR) can reconstruct realistic details, but they suffer severe performance degradation for low-light images because of their ignorance of negative effects of illumination, and even produce overexposure for unevenly illuminated images. I...