Deep learning-based image stitching method and apparatus

A deep learning-based image stitching apparatus, the apparatus comprising:

• a memory configured to store one or more instructions;
• and
• a processor configured to execute the instructions,
• wherein when the instructions are executed, the processor is configured to:
• receive a plurality of images comprising a first image and a second image to be stitched to the first image;
• extract a feature map of the plurality of images;
• generate a plurality of flow maps indicating movement information of pixels of the plurality of images, based on the feature map;
• generate a plurality of warping images in which the pixels of the plurality of images are moved, by applying the plurality of flow maps to the plurality of images, respectively;
• generate a plurality of weight maps for blending the plurality of warping images, based on the feature map, and
• generate a stitch image in which the first image and the second image are stitched, by blending the plurality of warping images based on the plurality of weight maps,
• wherein the plurality of flow maps comprising a first flow map indicating movement information of pixels of the first image and a second flow map indicating movement information of pixels of the second image.