Hui Huang, Yang Zhou, Dani Lischinski, Daniel Cohen-Or, Rongjun Xiao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
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
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2401.02847")
get_code_for_paper("2401.02847")
have("2401.02847")
Connect an agent — have() is free.