摘要:
An image restoration method includes determining degradation information indicating a degradation factor of a degraded image, tuning the degradation information based on a tuning condition, and generating a restored image corresponding to the degraded image by executing an image restoration network with the degraded image and the degradation information.
摘要:
An object detection method includes setting a first window region and a second window region larger than the first window region that correspond to partial regions of different sizes in an input image, downsampling the second window region to generate a resized second window region, detecting a first object candidate from the first window region and a second object candidate from the resized second window region, and detecting an object included in the input image based on one or both of the first object candidate and the second object candidate.
摘要:
A rendering method includes receiving resolution information including an optimal resolution for rendering images constituting a frame, a number of multi-samples, and resolution factors of the respective images (S310), rendering the images at the optimal resolution (S320), and adjusting a resolution of each of the rendered images based on the resolution factors and the number of multi-samples (S330).
摘要:
A method of adjusting a brightness of an image includes matching an object model to an object based on one or more feature points of the object extracted from an input image including the object; mapping a surface normal map in a two-dimensional (2D) image form to the input image based on the matched object model; and generating shadow information for the input image based on the mapped surface normal map and a virtual light source.