Bridging Global Context Interactions for High-Fidelity Image Completion
arXiv:2104.00845
Abstract
Bridging global context interactions correctly is important for high-fidelity image completion with large masks. Previous methods attempting this via deep or large receptive field (RF) convolutions cannot escape from the dominance of nearby interactions, which may be inferior. In this paper, we propose to treat image completion as a directionless sequence-to-sequence prediction task, and deploy a transformer to directly capture long-range dependence in the encoder. Crucially, we employ a restrictive CNN with small and non-overlapping RF for weighted token representation, which allows the transformer to explicitly model the long-range visible context relations with equal importance in all layers, without implicitly confounding neighboring tokens when larger RFs are used. To improve appearance consistency between visible and generated regions, a novel attention-aware layer (AAL) is introduced to better exploit distantly related high-frequency features. Overall, extensive experiments demonstrate superior performance compared to state-of-the-art methods on several datasets.
References in corpus (11)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Self-Attention Generative Adversarial Networks
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Visual Transformers: Token-based Image Representation and Processing for Computer Vision
- Masked Autoencoders Are Scalable Vision Learners
- SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
- Generative Adversarial Transformers
- High-Fidelity Pluralistic Image Completion with Transformers
- Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes