StructureFlow: Image Inpainting via Structure-aware Appearance Flow
arXiv:1908.03852
The paper introduces a two‑stage deep learning framework for image inpainting that first restores missing structures using edge‑preserved smooth images and then generates fine textures with an appearance‑flow based texture generator.
Abstract
Image inpainting techniques have shown significant improvements by using deep neural networks recently. However, most of them may either fail to reconstruct reasonable structures or restore fine-grained textures. In order to solve this problem, in this paper, we propose a two-stage model which splits the inpainting task into two parts: structure reconstruction and texture generation. In the first stage, edge-preserved smooth images are employed to train a structure reconstructor which completes the missing structures of the inputs. In the second stage, based on the reconstructed structures, a texture generator using appearance flow is designed to yield image details. Experiments on multiple publicly available datasets show the superior performance of the proposed network.