EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
Preprint
Abstract
Over the last few years, deep learning techniques have yielded significant improvements in image inpainting. However, many of these techniques fail to reconstruct reasonable structures as they are commonly over-smoothed and/or blurry. This paper develops a new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details. We propose a two-stage adversarial model EdgeConnect that comprises of an edge generator followed by an image completion network. The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori. We evaluate our model end-to-end over the publicly available datasets CelebA, Places2, and Paris StreetView, and show that it outperforms current state-of-the-art techniques quantitatively and qualitatively. Code and models available at: https://github.com/knazeri/edge-connectKeywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Free-Form Image Inpainting With Gated Convolution2019
- Globally and locally consistent image completionACM Transactions on Graphics, 2017
- Places: A 10 Million Image Database for Scene RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deconvolution and Checkerboard Artifacts2016
- Image completion using planar structure guidanceACM Transactions on Graphics, 2014
- Structured Learning and Prediction in Computer VisionFoundations and Trends in Computer Graphics and Vision, 2011
- Image Compression With Edge-Based InpaintingIEEE Transactions on Circuits and Systems for Video Technology, 2007
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Digital inpainting based on the Mumford–Shah–Euler image modelEuropean Journal of Applied Mathematics, 2002
- Filling-in by joint interpolation of vector fields and gray levelsIEEE Transactions on Image Processing, 2001