StructureFlow: Image Inpainting via Structure-Aware Appearance Flow

Yurui Ren, Xiaoming Yu, Ruonan Zhang, Thomas H. Li, Shan Liu, Ge Li; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 181-190

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Ren_2019_ICCV,
author = {Ren, Yurui and Yu, Xiaoming and Zhang, Ruonan and Li, Thomas H. and Liu, Shan and Li, Ge},
title = {StructureFlow: Image Inpainting via Structure-Aware Appearance Flow},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}