Extensor-based image and video interpolation and inpainting.

摘要

A new interpolation method for image and video interpolation and inpainting is introduced in this work and referred to as Extensor-based interpolation algorithm. The approach consists of a mapping from pixel index space to color space based on the low-resolution image so that non-integral pixel indices in a super-sampling can be mapped to colors. This mapping is based on an extensor-based transformation of 2D pixel indices to an N-dimensional vector space that encodes the Euclidean proximity interrelationships among a neighborhood of N pixels. Experimental results indicate that extensor-based interpolation yields results that are qualitatively superior to classical bilinear and bicubic interpolation, which has important advantages in comparison to edge-directed and optimal-recovery interpolation methods. This algorithm is applied into image and video inpainting and produces satisfactory results at lower computational cost.