Abstract: An image compression method includes obtaining a hidden variable of an input image using a coding network of a deep learning neural network comprising at least one downsampling back projection module including performing downsampling transformation on a first feature map of the input image input to the downsampling back projection module to obtain a second feature map, obtaining a third feature map having a same resolution as a resolution of the first feature map by reconstructing the second feature map, and obtaining a fourth feature map as an optimization result of the second feature map, based on a difference value between the first feature map and the third feature map; and obtaining a bitstream file of a compressed image by performing entropy coding based on the hidden variable obtained based on the fourth feature map of a last downsampling back projection module.

Abstract: A method and a system for single-shot multi-frame ultrafast terahertz imaging of a scene, the method comprising generating a pump beam and a probe beam: generating a THz beam from the pump beam and passing the THz beam through the scene: multiplexing the probe beam in the time domain and in the spatial-frequency domain. yielding a multiplexed probe beam; detecting a THz beam passing through the scene: guiding the multiplexed probe beam to a THz detection crystal and converting the multiplexed probe beam into mutually orthogonal linear polarized beams: guiding the mutually orthogonal linear polarized beams to a camera: and recovering frames of the scene from multiplexed images acquired by the camera.

Abstract: A processor-implemented method includes determining weights of a plurality of channel blocks comprised in a neural network to encode an image, selecting one or more channel blocks from the plurality of channel blocks to encode the image based on the weights and a compression rate of the image, and generating an encoded image by encoding the image using a sub-neural network comprising channels comprised in the one or more channel blocks.

Abstract: A method of estimating an optical flow includes processing, using an image processing pass, a first image and a second image separately, and estimating the optical flow based on a second image attention feature map of the first image and a second image attention feature map of the second image. The processing using the image processing pass includes extracting a feature map by encoding an image, outputting a first image fusion attention feature map by fusing row relationship information of the image with the image feature map, outputting a first image attention feature map of the image based on the first image fusion attention feature map and the image feature map, outputting a second image fusion attention feature map by fusing column relationship information of the image with the first image attention feature map, and generating a second image attention feature map of the image based on the second image fusion attention feature map and the first image attention feature map.

Abstract: An image compression method includes obtaining a hidden variable of an input image using a coding network of a deep learning neural network comprising at least one downsampling back projection module including performing downsampling transformation on a first feature map of the input image input to the downsampling back projection module to obtain a second feature map, obtaining a third feature map having a same resolution as a resolution of the first feature map by reconstructing the second feature map, and obtaining a fourth feature map as an optimization result of the second feature map, based on a difference value between the first feature map and the third feature map; and obtaining a bitstream file of a compressed image by performing entropy coding based on the hidden variable obtained based on the fourth feature map of a last downsampling back projection module.