2022/12/20 by Siyu Huang, Huang, Siyu, Jie An +7 · 4 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Art #Artificial intelligence #Centroid #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Engineering #FOS: Computer and information sciences #FOS: Electrical engineering #Fidelity #Generative Adversarial Networks and Image Synthesis #High fidelity #Image (mathematics) #Image Enhancement Techniques #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Multimedia (cs.MM) #Representation (politics) #Similarity (geometry) #Style (visual arts) #Transfer (computing) #Vector quantization #Visual arts #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2212.10431
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2022/12/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to push the generated image toward high similarities in both content and style. However, this type of approach cannot guarantee visual fidelity, i.e., the generated artworks should be indistinguishable from real ones. In this paper, we devise a new style transfer framework called QuantArt for high visual-fidelity stylization. QuantArt pushes the latent representation of the generated artwork toward the centroids of the real artwork distribution with vector quantization. By fusing the quantized and continuous latent representations, QuantArt allows flexible control over the generated artworks in terms of content preservation, style similarity, and visual fidelity. Experiments on various style transfer settings show that our QuantArt framework achieves significantly higher visual fidelity compared with the existing style transfer methods.