𝗗𝗮𝘆-𝟰𝟭𝟴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis by Adobe Research Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published arxiv 2022. 👉 Propose a novel U-Attention network with multi-stage hourglass vision Transformers enabling 2× texture synthesis on a broad range of texture patterns with a single trained network. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ✔️ 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 multi-stage hourglass backbone that attends to the global structure and performs patch mapping at varying scales in a coarse-to-fine-to-coarse stream. ✔️ Further completed by skip connection and convolution designs that propagate and fuse information at different scales, our U-Attention architecture unifies attention to microstructures, mesostructures and macrostructures, and progressively refines synthesis results at successive stages. ✔️ We show that our method achieves stronger 2× 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. #computervision #artificialintelligence #data
Great share +