This paper presents a computational framework for quantifying aesthetics of Chinese ink wash and applying them to generative models.We define differentiable metrics for the three core elements:the compositional balanc...This paper presents a computational framework for quantifying aesthetics of Chinese ink wash and applying them to generative models.We define differentiable metrics for the three core elements:the compositional balance of“Liubai”(negative space),the calligraphic quality of“Bichu”(brushstroke),and the tonal diffusion of“Moyun”(ink wash).Using these metrics,we benchmark unpaired image-to-image systems—CycleGAN,MUNIT,ChipGAN,and diffusion pipelines with controllable methods(Style LoRA,ControlNet-Tile,IP-Adapter)—on photo-to-ink transfer.Results show a trade-off:diffusion excels at“Moyun”texture fidelity,while ChipGAN with explicit aesthetic losses better preserves“Liubai”and“Bichu”structure.The study also highlights limitations of generic image-quality metrics(e.g.,FID)for artistic evaluation.We further validate implications for phygital textile design via seamless-tiling tests and small-scale physical samples.Finally,we outline a unified,material-aware scheme embedding fabric diffusion physics(Fick’s law)into a Physics-Informed GAN objective to jointly optimize aesthetic fidelity and printability.展开更多
Simulating the traditional painting art by computer graphics is a challenging and attractive subject. Basing on the experience in the ink wash drawing, in this paper, we expound the artistic characters of ink wash p...Simulating the traditional painting art by computer graphics is a challenging and attractive subject. Basing on the experience in the ink wash drawing, in this paper, we expound the artistic characters of ink wash painting and particularly analyze the characteristics of the materials used in the ink wash drawing and the relationships between them. A simulation model is presented and some typical visual effects of the ink wash painting are realized.展开更多
文摘This paper presents a computational framework for quantifying aesthetics of Chinese ink wash and applying them to generative models.We define differentiable metrics for the three core elements:the compositional balance of“Liubai”(negative space),the calligraphic quality of“Bichu”(brushstroke),and the tonal diffusion of“Moyun”(ink wash).Using these metrics,we benchmark unpaired image-to-image systems—CycleGAN,MUNIT,ChipGAN,and diffusion pipelines with controllable methods(Style LoRA,ControlNet-Tile,IP-Adapter)—on photo-to-ink transfer.Results show a trade-off:diffusion excels at“Moyun”texture fidelity,while ChipGAN with explicit aesthetic losses better preserves“Liubai”and“Bichu”structure.The study also highlights limitations of generic image-quality metrics(e.g.,FID)for artistic evaluation.We further validate implications for phygital textile design via seamless-tiling tests and small-scale physical samples.Finally,we outline a unified,material-aware scheme embedding fabric diffusion physics(Fick’s law)into a Physics-Informed GAN objective to jointly optimize aesthetic fidelity and printability.
文摘Simulating the traditional painting art by computer graphics is a challenging and attractive subject. Basing on the experience in the ink wash drawing, in this paper, we expound the artistic characters of ink wash painting and particularly analyze the characteristics of the materials used in the ink wash drawing and the relationships between them. A simulation model is presented and some typical visual effects of the ink wash painting are realized.
