Abstract: A implicit structured light decoding method, a computer equipment and a computer-readable storage medium. The method includes: traversing an image captured by a camera to acquire a grayscale value of each pixel point and an ideal neighborhood grayscale distribution; extracting and outputting an updated output image according to the grayscale value of each pixel point and the ideal neighborhood grayscale distribution and in combination with a preset output image; classifying stripe central points in the updated output image into different stripes; determining a correspondence between stripes in the updated output image and stripes in a structured light image according to the different stripes; and decoding all stripe central points by using triangulation method in combination with the correspondence between the extracted stripes and the projected stripe pattern. This solution can efficiently and robustly decode the implicit stripe-based structured light on a basis of ensuring precision.

Abstract: A video blind denoising method based on deep learning, a computer device and a computer-readable storage medium. The method includes: taking a video sequence from a video to be denoised, taking the middle frame in the video sequence as a noisy reference frame, performing an optical flow estimation on the image corresponding to the noisy reference frame and each other frame in the video sequence, to obtain optical flow fields; transforming, according to the optical flow fields, the image corresponding to each other frame in the video sequence to the noisy reference frame for registration respectively, to obtain multi-frame noisy registration images; taking the multi-frame noisy registration images as an input of a convolutional neural network, taking the noisy reference frame as the reference image, performing iterative training and denoising by using the noise2noise training principle, to obtain the denoised image. This solution may achieve the blind denoising of a video.

Abstract: A video blind denoising method based on deep learning, a computer device and a computer-readable storage medium. The method includes: taking a video sequence from a video to be denoised, taking the middle frame in the video sequence as a noisy reference frame, performing an optical flow estimation on the image corresponding to the noisy reference frame and each other frame in the video sequence, to obtain optical flow fields; transforming, according to the optical flow fields, the image corresponding to each other frame in the video sequence to the noisy reference frame for registration respectively, to obtain multi-frame noisy registration images; taking the multi-frame noisy registration images as an input of a convolutional neural network, taking the noisy reference frame as the reference image, performing iterative training and denoising by using the noise2noise training principle, to obtain the denoised image. This solution may achieve the blind denoising of a video.

Abstract: A implicit structured light decoding method, a computer equipment and a computer-readable storage medium. The method includes: traversing an image captured by a camera to acquire a grayscale value of each pixel point and an ideal neighborhood grayscale distribution; extracting and outputting an updated output image according to the grayscale value of each pixel point and the ideal neighborhood grayscale distribution and in combination with a preset output image; classifying stripe central points in the updated output image into different stripes; determining a correspondence between stripes in the updated output image and stripes in a structured light image according to the different stripes; and decoding all stripe central points by using triangulation method in combination with the correspondence between the extracted stripes and the projected stripe pattern. This solution can efficiently and robustly decode the implicit stripe-based structured light on a basis of ensuring precision.