Generating Non-Stationary Textures using Self-Rectification
This addresses the problem of generating complex textures for applications like computer graphics and design, representing a strong domain-specific improvement.
The paper tackles the challenge of synthesizing non-stationary textures from examples by introducing a two-step method where users edit a reference texture and then use self-rectification to refine it into a seamless output, demonstrating significant advancements over state-of-the-art techniques.
This paper addresses the challenge of example-based non-stationary texture synthesis. We introduce a novel twostep approach wherein users first modify a reference texture using standard image editing tools, yielding an initial rough target for the synthesis. Subsequently, our proposed method, termed "self-rectification", automatically refines this target into a coherent, seamless texture, while faithfully preserving the distinct visual characteristics of the reference exemplar. Our method leverages a pre-trained diffusion network, and uses self-attention mechanisms, to gradually align the synthesized texture with the reference, ensuring the retention of the structures in the provided target. Through experimental validation, our approach exhibits exceptional proficiency in handling non-stationary textures, demonstrating significant advancements in texture synthesis when compared to existing state-of-the-art techniques. Code is available at https://github.com/xiaorongjun000/Self-Rectification