Contextual-based Image Inpainting: Infer, Match, and Translate
This addresses the problem of filling missing regions in images for applications like photo editing, but it is incremental as it builds on existing techniques with a novel decomposition.
The paper tackles image inpainting by proposing a learning-based approach that divides the task into inference and translation steps using deep neural networks, achieving better visual quality than previous state-of-the-art methods on public datasets.
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 inference and translation as two separate steps and model each step with a deep neural network. We also use simple heuristics to guide the propagation of local textures from the boundary to the hole. We show that, by using such techniques, inpainting reduces to the problem of learning two image-feature translation functions in much smaller space and hence easier to train. We evaluate our method on several public datasets and show that we generate results of better visual quality than previous state-of-the-art methods.