Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis
Year: 2022
Type: preprint
Abstract: We present a novel U-Attention vision Transformer for universal texture synthesis. We exploit the natural long-range dependencies enabled by the attention mechanism to allow our approach to synthesize diverse textures while preserving their structures in a single inference. We propose a hierarchical hourglass backbone that attends to the global structure and performs patch mapping at varying scales in a coarse-to-fine-to-coarse stream. Completed by skip connection and convolution designs that propagate and fuse information at different scales, our hierarchical U-Attention architecture unifies attention to features from macro structures to micro details, and progressively refines synthesis results at successive stages. Our method achieves stronger 2$\times$ synthesis than previous work on both stochastic and structured textures while generalizing to unseen textures without fine-tuning. Ablation studies demonstrate the effectiveness of each component of our architecture.
Source: arXiv (Cornell University)
Authors: Guo, Shouchang, Deschaintre, Valentin, Noll, Douglas, Roullier, Arthur
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4226394065