Yiyi Long
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiyi Long has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Chenshu Xu
Singapore Management University Singapore Singapore
1 shared publication- Chenxi Zheng
South China University of Technology Guangzhou China
1 shared publication Chuhua Xian
South China University of Technology Guangzhou China
1 shared publicationJingxin Liang
South China University of Technology Guangzhou China
1 shared publication- Rui Yang
School of Computer Sciences, Shaanxi Normal University, Xian, China
1 shared publication Shengfeng He
Singapore Management University Singapore Singapore
1 shared publication
Latest Publications
- 23 April 2026
- Published by Wiley in Computer Graphics Forum
SketchCrafter: Sketch Extraction as a Training‐Free Generative Process
We introduce SketchCrafter, a training‐free framework that formulates sketch extraction as a generative process rather than relying on aggregation. SketchCrafter initiates generation with an edge‐based initialization, projecting edge features from the content image into the diffusion latent space to create a structured noise foundation. This foundation enables controlled integration of style and content, achieving high fidelity to both the source image and reference style. A dual‐control mechanism ensures coherence at multiple levels: locally, content features fuse with edge structures to preserve fine details, while globally, a content encoder reinforces structural alignment. Style information is integrated in parallel, with key and value tokens capturing fine stylistic details, supported by a global style encoder for overall consistency. Experiments show that SketchCrafter excels in content alignment and style fidelity across benchmarks, proving it as an effective solution for training‐free sketch extraction.
- 23 April 2026
- Published by Wiley in Computer Graphics Forum
SketchCrafter: Sketch Extraction as a Training‐Free Generative Process
We introduce SketchCrafter, a training‐free framework that formulates sketch extraction as a generative process rather than relying on aggregation. SketchCrafter initiates generation with an edge‐based initialization, projecting edge features from the content image into the diffusion latent space to create a structured noise foundation. This foundation enables controlled integration of style and content, achieving high fidelity to both the source image and reference style. A dual‐control mechanism ensures coherence at multiple levels: locally, content features fuse with edge structures to preserve fine details, while globally, a content encoder reinforces structural alignment. Style information is integrated in parallel, with key and value tokens capturing fine stylistic details, supported by a global style encoder for overall consistency. Experiments show that SketchCrafter excels in content alignment and style fidelity across benchmarks, proving it as an effective solution for training‐free sketch extraction.