在基于变压器的智能染方法下,镜像绘画的数字交互设计
1College of Arts, Zhejiang Shuren University, Hangzhou, 310000, Zhejiang Province, China. zcy2276230908@zjsru.edu.cn.
Scientific reports
|July 15, 2025
概括
这项研究介绍了一种新的Mamba-Swin-Low-Rank适应 (LoRA) 框架,用于智能镜像绘画染. 该方法提高了数字艺术应用的图像质量和计算效率.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 数字艺术 数字艺术 数字艺术
背景情况:
- 镜像绘画的智能染面临着局部纹理忠实性和全球风格一致性方面的挑战.
- 目前的方法,如StyleSwin,SANet和稳定扩散与结构一致性,风格漂移和计算需求作斗争.
研究的目的:
- 开发一种高质量的实时智能染方法,用于镜像绘画.
- 解决现有方法在平衡速度和图像质量的局限性.
主要方法:
- 提出了Mamba-Swin-Low-Rank 适应 (LoRA) 染框架.
- 利用Mamba状态空间模型进行局部特征提取 (保留笔触/边缘).
- 使用Swin变压器,具有滑动窗口注意力,以实现高效的全球特征建模.
- 集成的LoRA,用于优化风格转移,并提高参数效率.
主要成果:
- 实现了高图像质量指标:34.2dB PSNR,0.91 SSIM,0.18 LPIPS. 这是一个很好的结果.
- 在图像质量和计算效率方面,在主流方法上表现出优越的性能.
- 展示了改进的交互体验和实际应用潜力.
结论:
- 马巴-斯温-洛拉框架有效地平衡了智能镜像绘画染中的速度和质量.
- 该方法对数字艺术,HCI和游戏艺术的应用有显著的前景.
- 为复杂的染任务提供计算效率高,高保真度的解决方案.
相关概念视频
01:23Design Example
The innovation of touch-tone telephony revolutionized the telecommunications industry by replacing the traditional rotary dial with a dual-tone multi-frequency (DTMF) signaling system. This system uses a matrix-style keypad with buttons arranged in four rows and three columns, creating 12 distinct signals each assigned to a pair of frequencies. Each button press results in a simultaneous generation of two sinusoidal tones – one from a low-frequency group (697 to 941 Hz) and one from a...
01:20Transformations of Functions III
Transformations modify the graphical representation of a function without changing its fundamental form. One common transformation is reflection, which flips the graph across a designated axis. When the vertical coordinates of all points are multiplied by the negative one, the entire graph is mirrored over the horizontal axis. This transformation reverses the vertical orientation of peaks and troughs, akin to signal inversion in electrical systems, where a waveform is flipped, but the timing of...