Burst-Enhanced Super-Resolution Network (BESR)
Sensors · 23.03.2024 · 24 (7) · 2052
DOI: 10.3390/s24072052 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 23.03.2024. Verfasst von Jiaao Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Aerospace Information Research Institute, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Program Project of Science and Technology Innovation of the Chinese Academy of Sciences, Innovation Foundation of the Key Laboratory of Computational Optical Imaging Technology, CAS.
Abstract (Originalsprache)
Multi-frame super-resolution (MFSR) leverages complementary information between image sequences of the same scene to increase the resolution of the reconstructed image. As a branch of MFSR, burst super-resolution aims to restore image details by leveraging the complementary information between noisy sequences. In this paper, we propose an efficient burst-enhanced super-resolution network (BESR). Specifically, we introduce Geformer, a gate-enhanced transformer, and construct an enhanced CNN-Transformer block (ECTB) by combining convolutions to enhance local perception. ECTB efficiently aggregates intra-frame context and inter-frame correlation information, yielding an enhanced feature representation. Additionally, we leverage reference features to facilitate inter-frame communication, enhancing spatiotemporal coherence among multiple frames. To address the critical processes of inter-frame alignment and feature fusion, we propose optimized pyramid alignment (OPA) and hybrid feature fusion (HFF) modules to capture and utilize complementary information between multiple frames to recover more high-frequency details. Extensive experiments demonstrate that, compared to state-of-the-art methods, BESR achieves higher efficiency and competitively superior reconstruction results. On the synthetic dataset and real-world dataset of BurstSR, our BESR achieves PSNR values of 42.79 dB and 48.86 dB, respectively, outperforming other MFSR models significantly.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Aerospace Information Research Institute, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China.
- School of Optoelectronics, University of Chinese Academy of Sciences, No. 19(A) Yuquan Road, Shijingshan District, Beijing 100049, China.
- Department of Key Laboratory of Computational Optical Imagine Technology, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China.
Förderung
- Key Program Project of Science and Technology Innovation of the Chinese Academy of Sciences
- Innovation Foundation of the Key Laboratory of Computational Optical Imaging Technology, CAS
Zitieren
APA
Li, J., Lv, Q., Zhang, W., Zhang, Y., & Tan, Z. (2024). Burst-Enhanced Super-Resolution Network (BESR). Sensors, 24(7), 2052. https://doi.org/10.3390/s24072052
Vancouver
Li J, Lv Q, Zhang W, Zhang Y, Tan Z. Burst-Enhanced Super-Resolution Network (BESR). Sensors. 2024;24(7):2052. doi:10.3390/s24072052
BibTeX
@article{Li2024,
author = {Li, Jiaao and Lv, Qunbo and Zhang, Wenjian and Zhang, Yu and Tan, Zheng},
title = {Burst-Enhanced Super-Resolution Network (BESR)},
journal = {Sensors},
year = {2024},
volume = {24},
number = {7},
pages = {2052},
doi = {10.3390/s24072052}
}
EUVIMED