CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

TL;DR

CM-GAN introduces a cascaded modulation GAN with object-aware training that effectively handles large holes in complex images, improving structure plausibility and object removal capabilities.

Contribution

The paper proposes a novel cascaded modulation GAN architecture with Fourier convolution and an object-aware training scheme for improved image inpainting.

Findings

Outperforms existing methods in quantitative metrics

Achieves more plausible and semantically consistent inpainting results

Effectively prevents hallucination of new objects in holes

Abstract

Recent image inpainting methods have made great progress but often struggle to generate plausible image structures when dealing with large holes in complex images. This is partially due to the lack of effective network structures that can capture both the long-range dependency and high-level semantics of an image. We propose cascaded modulation GAN (CM-GAN), a new network design consisting of an encoder with Fourier convolution blocks that extract multi-scale feature representations from the input image with holes and a dual-stream decoder with a novel cascaded global-spatial modulation block at each scale level. In each decoder block, global modulation is first applied to perform coarse and semantic-aware structure synthesis, followed by spatial modulation to further adjust the feature map in a spatially adaptive fashion. In addition, we design an object-aware training scheme to prevent the network from hallucinating new objects inside holes, fulfilling the needs of object removal tasks in real-world scenarios. Extensive experiments are conducted to show that our method significantly outperforms existing methods in both quantitative and qualitative evaluation. Please refer to the project page: \url{https://github.com/htzheng/CM-GAN-Inpainting}.