Generating Non-Stationary Textures using Self-Rectification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929227841929216 |
|---|---|
| author | Zhou, Yang Xiao, Rongjun Lischinski, Dani Cohen-Or, Daniel Huang, Hui |
| author_facet | Zhou, Yang Xiao, Rongjun Lischinski, Dani Cohen-Or, Daniel Huang, Hui |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_02847 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating Non-Stationary Textures using Self-Rectification Zhou, Yang Xiao, Rongjun Lischinski, Dani Cohen-Or, Daniel Huang, Hui Computer Vision and Pattern Recognition Graphics Machine Learning 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 |
| title | Generating Non-Stationary Textures using Self-Rectification |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2401.02847 |