EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning

TL;DR

EdgeConnect introduces a two-stage adversarial model for image inpainting that hallucinate edges and fill missing regions, significantly improving the reconstruction of fine details over existing methods.

Contribution

The paper presents a novel two-stage adversarial framework combining edge hallucination and image completion for superior inpainting results.

Findings

Outperforms state-of-the-art methods quantitatively.

Produces more realistic and detailed inpainted images.

Effective on diverse datasets like CelebA, Places2, and Paris StreetView.

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-connect