Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting

TL;DR

This paper introduces a novel Contextual Residual Aggregation mechanism that enables high-resolution image inpainting by operating on low-resolution inputs, significantly reducing memory requirements while maintaining high-quality, detailed results on 8K images.

Contribution

The proposed CRA method allows high-resolution inpainting using low-resolution training, reducing memory usage and enabling real-time processing of 8K images.

Findings

Effective high-resolution inpainting up to 8K images.

Significant reduction in memory and computational costs.

Real-time performance on 2K images with high-quality results.

Abstract

Recently data-driven image inpainting methods have made inspiring progress, impacting fundamental image editing tasks such as object removal and damaged image repairing. These methods are more effective than classic approaches, however, due to memory limitations they can only handle low-resolution inputs, typically smaller than 1K. Meanwhile, the resolution of photos captured with mobile devices increases up to 8K. Naive up-sampling of the low-resolution inpainted result can merely yield a large yet blurry result. Whereas, adding a high-frequency residual image onto the large blurry image can generate a sharp result, rich in details and textures. Motivated by this, we propose a Contextual Residual Aggregation (CRA) mechanism that can produce high-frequency residuals for missing contents by weighted aggregating residuals from contextual patches, thus only requiring a low-resolution prediction from the network. Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed. Moreover, the need for high-resolution training datasets is alleviated. In our experiments, we train the proposed model on small images with resolutions 512x512 and perform inference on high-resolution images, achieving compelling inpainting quality. Our model can inpaint images as large as 8K with considerable hole sizes, which is intractable with previous learning-based approaches. We further elaborate on the light-weight design of the network architecture, achieving real-time performance on 2K images on a GTX 1080 Ti GPU. Codes are available at: Atlas200dk/sample-imageinpainting-HiFill.