In: Proceedings of the AAAI conference on artificial intelligence, vol 32 Song L, Zhang M, Wu X, He R (2018) Adversarial discriminative heterogeneous face recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7930–7938įu C, Wu X, Hu Y, Huang H, He R (2019) Dual variational generation for low shot heterogeneous face recognition. IEEE Trans Instrum Meas 72:1–11ĭuan B, Fu C, Li Y, Song X, He R (2020) Cross-spectral face hallucination via disentangling independent factors. Tomar AS, Arya K, Rajput SS (2023) Deep hyfeat based attention in attention model for face super-resolution. Commun ACM 63(11):139–144Īggarwal K, Mijwil MM, Al-Mistarehi A-H, Alomari S, Gök M, Alaabdin AMZ, Abdulrhman SH et al (2022) Has the future started? the current growth of artificial intelligence, machine learning, and deep learning. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2020) Generative adversarial networks. Kumar S, Singh SK, Mishra NK, Dutta M (2022) An encoder-decoder based thermo-visible image translation for disguised and undisguised faces. Rai D, Rajput SS (2022) Robust face hallucination algorithm using motion blur embedded nearest proximate patch representation. Luo M, Wu H, Huang H, He W, He R (2022) Memory-modulated transformer network for heterogeneous face recognition. Xiao W, Zhang Y, Wang H, Li F, Jin H (2022) Heterogeneous knowledge distillation for simultaneous infrared-visible image fusion and super-resolution. Experimental results demonstrate that GDANet outperforms state-of-the-art methods, showing its effectiveness in handling real-world low-quality thermal images across diverse practical applications. This approach allows GDANet to adapt spatial features based on the degradation representation, striking a balance between fidelity and texture faithfulness using degradation-aware feature fusion (DAFF) blocks. Additionally, an unsupervised degradation representation learning scheme is developed to capture abstract degradation representations of degraded thermal images in a representation space. GDANet combines pretrained Generative Adversarial Network (GAN) blocks with a U-shaped deep neural network (DNN) to incorporate faithful facial priors, including geometry, facial textures, and colors. To address these issues, we propose the Generative Facial Prior Embedded Degradation Adaption Network (GDANet), which synthesizes high-quality visible images from low-quality thermal images. Current methods assume similar resolutions and noise-free conditions between thermal and visible images, limiting their applicability. In real-world long-range surveillance systems, thermal face images captured from a distance suffer from low resolution and noise, posing challenges for thermal-to-visible face image translation.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |