Based on the auto-encoder, shallow and deep auto-encoders with residual concept are constructed. The effects of different depth auto-encoders on large-field of view infrared image reconstruction are discussed under four conditions: no sparse constraint, regularization constraint, KL divergence sparse constraint and both constraints. From the reconstructed image quality and index parameters, it can be concluded that with the increase of the auto-encoder depth, sparse constraints have a greater impact on the reconstruction effect of the network.
Super-resolution of large field of view infrared image based on convolutional sparse auto-encoder
Ninth Symposium on Novel Photoelectronic Detection Technology and Applications ; 2022 ; Hefei,China
Proc. SPIE ; 12617
2023-04-04
Conference paper
Electronic Resource
English
Super-resolution of large field of view infrared image based on residual convolutional auto-encoders
British Library Conference Proceedings | 2023
|Infrared long-wave multispectral image reconstruction based on auto-encoder network
British Library Conference Proceedings | 2019
|