One-Shot Reference-based Structure-Aware Image to Sketch Synthesis

Authors: Rui Yang, Honghong Yang, Li Zhao, Qin Lei, Mianxiong Dong, Kaoru Ota, Xiaojun Wu

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our model demonstrates superior performance across multiple evaluation metrics, including user style preference. Extensive experiments conducted on various standard benchmarks demonstrate our superiority in terms of sketch quality, flexibility, and applicability.
Researcher Affiliation Academia 1 Key Laboratory of Intelligent Computing and Service Technology for Folk Song, Ministry of Culture and Tourism, School of Computer Science, Shaanxi Normal University, Xi an, 710119, China 2College of Computer Science, Chongqing University, Chongqing, 400044, China 3Muroran Institute of Technology, Muroran, Hokkaido, 0508585, Japan
Pseudocode No The paper only describes the methodology in prose and mathematical formulas, without explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code https://github.com/Ref2Sketch-SA
Open Datasets Yes Datasets: Four datasets were used for evaluation: 4SKST (Seo, Ashtari, and Noh 2023), FS2K (Fan et al. 2022), Anime (Kang 2018), and APDrawings (Yi et al. 2019).
Dataset Splits No The paper mentions several datasets (4SKST, FS2K, Anime, APDrawings) used for evaluation but does not specify how these datasets were split into training, validation, or test sets.
Hardware Specification Yes All experiments were conducted on a single NVIDIA 3090 GPU
Software Dependencies No The paper mentions using Stable Diffusion XL (SDXL) and IP-Adapter, but does not provide specific version numbers for these or other software dependencies like Python, PyTorch, or CUDA.
Experiment Setup Yes Specifically, the sampling result zt 1 in each denoising operation is altered by ˆzt 1: ˆzt 1 = zt 1 ζ zt Lacu, (11) where ζ is set to 3.