GAN-based Vision Transformer for High-Quality Thermal Image Enhancement

被引:2
|
作者
Marnissi, Mohamed Amine [1 ]
Fathallah, Abir [2 ]
机构
[1] Univ Sfax, Ecole Natl Ingn Sfax, Sfax 3038, Tunisia
[2] Inst Polytech Paris, Samovar, CNRS, Telecom SudParis, 9 Rue Charles Fourier, F-91011 Evry, France
关键词
D O I
10.1109/CVPRW59228.2023.00089
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Generative Adversarial Networks (GANs) have shown an outstanding ability to generate high-quality images with visual realism and similarity to real images. This paper presents a new architecture for thermal image enhancement. Precisely, the strengths of architecture-based vision transformers and generative adversarial networks are exploited. The thermal loss feature introduced in our approach is specifically used to produce high-quality images. Thermal image enhancement also relies on fine-tuning based on visible images, resulting in an overall improvement in image quality. A visual quality metric was used to evaluate the performance of the proposed architecture. Significant improvements were found over the original thermal images and other enhancement methods established on a subset of the KAIST dataset. The performance of the proposed enhancement architecture is also verified on the detection results by obtaining better performance with a considerable margin regarding different versions of the YOLO detector.
引用
收藏
页码:817 / 825
页数:9
相关论文
共 50 条
  • [1] REVOLUTIONIZING THERMAL IMAGING: GAN-BASED VISION TRANSFORMERS FOR IMAGE ENHANCEMENT
    Marnissi, Mohamed Amine
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 2735 - 2739
  • [2] GAN-Based High-Quality Face-Swapping Composite Network
    Man, Qiaoyue
    Cho, Young-Im
    Gee, Seok-Jeong
    Kim, Woo-Je
    Jang, Kyoung-Ae
    [J]. ELECTRONICS, 2024, 13 (15)
  • [3] IMPROVING GAN-BASED VOCODER FOR FAST AND HIGH-QUALITY SPEECH SYNTHESIS
    He, Mengnan
    Guo, Tingwei
    Lu, Zhengxin
    Zhang, Ruixiong
    Gong, Caixia
    [J]. INTERSPEECH 2022, 2022, : 1601 - 1605
  • [4] Detail Fusion GAN: High-Quality Translation for Unpaired Images with GAN-based Data Augmentation
    Li, Ling
    Li, Yaochen
    Wu, Chuan
    Dong, Hang
    Jiang, Peilin
    Wang, Fei
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 1731 - 1736
  • [5] A Dual GAN-Based Method for Augmenting High-Quality Rice Leaf Disease Images
    Vijayalakshmi, K.
    Sreenivasulu, K.
    Sandhya, M.
    Khaleelbasha, G.
    Naresh, M. Venkata
    [J]. 2024 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATION AND APPLIED INFORMATICS, ACCAI 2024, 2024,
  • [6] Improved performance of GaN-based light-emitting diodes with high-quality GaN grown on InN islands
    Lee, Sang-Jun
    Cho, Chu-Young
    Hong, Sang-Hyun
    Han, Sang-Heon
    Yoon, Sukho
    Park, Yongjo
    Park, Seong-Ju
    [J]. JOURNAL OF PHYSICS D-APPLIED PHYSICS, 2011, 44 (42)
  • [7] Real-Time GAN-Based Model for Underwater Image Enhancement
    Avola, Danilo
    Cannistraci, Irene
    Cascio, Marco
    Cinque, Luigi
    Diko, Anxhelo
    Distante, Damiano
    Foresti, Gian Luca
    Mecca, Alessio
    Scagnetto, Ivan
    [J]. IMAGE ANALYSIS AND PROCESSING, ICIAP 2023, PT I, 2023, 14233 : 412 - 423
  • [8] High quality GaN-based Schottky barrier diodes
    Lee, K. H.
    Chang, S. J.
    Chang, P. C.
    Wang, Y. C.
    Kuo, C. H.
    [J]. APPLIED PHYSICS LETTERS, 2008, 93 (13)
  • [9] Improvement of Dynamic On-Resistance in GaN-Based Devices with a High-Quality In Situ SiN Passivation Layer
    Kim, Jeong-Gil
    Lee, Jun-Hyeok
    Kang, Dong-Min
    Lee, Jung-Hee
    [J]. MICROMACHINES, 2023, 14 (06)
  • [10] A High-Quality Rice Leaf Disease Image Data Method Based on a Dual GAN
    Zhang, Zhao
    Gao, Quan
    Liu, Lirong
    He, Yun
    [J]. IEEE ACCESS, 2023, 11 : 21176 - 21191