StructureFlow: Image Inpainting via Structure-aware Appearance Flow

TL;DR

StructureFlow introduces a two-stage image inpainting model that separately reconstructs structures and generates textures, leading to improved results in restoring both structure and fine details.

Contribution

The paper presents a novel two-stage framework that explicitly separates structure reconstruction from texture generation, enhancing inpainting quality.

Findings

Outperforms existing methods on multiple datasets

Effectively reconstructs missing structures

Restores fine-grained textures with high fidelity

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.