Interactive Image Inpainting Using Semantic Guidance

TL;DR

This paper introduces a user-guided image inpainting method that combines neural network priors with user input to produce customizable and high-quality inpainting results, enhancing controllability over traditional approaches.

Contribution

The proposed two-stage approach uniquely integrates neural network priors with user guidance, enabling customizable inpainting results with improved quality and controllability.

Findings

Outperforms existing methods in inpainting quality.

Provides effective user control over inpainting results.

Demonstrates superior controllability and visual coherence.

Abstract

Image inpainting approaches have achieved significant progress with the help of deep neural networks. However, existing approaches mainly focus on leveraging the priori distribution learned by neural networks to produce a single inpainting result or further yielding multiple solutions, where the controllability is not well studied. This paper develops a novel image inpainting approach that enables users to customize the inpainting result by their own preference or memory. Specifically, our approach is composed of two stages that utilize the prior of neural network and user's guidance to jointly inpaint corrupted images. In the first stage, an autoencoder based on a novel external spatial attention mechanism is deployed to produce reconstructed features of the corrupted image and a coarse inpainting result that provides semantic mask as the medium for user interaction. In the second stage, a semantic decoder that takes the reconstructed features as prior is adopted to synthesize a fine inpainting result guided by user's customized semantic mask, so that the final inpainting result will share the same content with user's guidance while the textures and colors reconstructed in the first stage are preserved. Extensive experiments demonstrate the superiority of our approach in terms of inpainting quality and controllability.