Image Inpainting using Multi-Scale Feature Image Translation
share
We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents. To this end, we propose a learning-based approach to generate visually coherent completion given a high-resolution image with missing components. In order to overcome the difficulty to directly learn the distribution of high-dimensional image data, we divide the task into initialization and texture-refinement as two separate steps and model each step with a deep neural network. We also use simple heuristics to guide transferring of textures from boundary to the hole. We show that, by using such techniques, inpainting reduces to the problem of learning two image-feature translation functions of much smaller dimensionality. We evaluate our method on several public datasets and show that we not only generate results of comparable or better visual quality, but are orders of magnitude faster than previous state-of-the-art methods.
READ FULL TEXT