FreqPose:频率感知扩散与分数格博过器和全球姿势-语义对齐.
Meng Wang1, Bing Wang1, Huiling Chen2
1Faculty of Information Engineering and Automation, Kunming University of Science and Technology, 727 South Jingming Road, Kunming 650500, China.
Sensors (Basel, Switzerland)
|February 27, 2026
概括
本研究介绍了一种基于扩散的生成框架,用于姿势引导的人形象生成,增强纹理细节,并在姿势变化期间保持语义身份. 这种新的方法提高了图像的真实性和一致性,优于现有的方法.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 图像生成 图像生成
背景情况:
- 姿势引导的人形象生成在姿势过渡期间面临着在保持高频纹理细节和语义身份方面的挑战.
- 现有的方法经常在姿势变化过程中扎在模糊性和细节丢失的外观转移和一致性上.
研究的目的:
- 提出一种基于扩散的新型生成框架,以解决姿势引导人图像生成中的纹理细节损失和语义不一致.
- 为了提高图像细节的真实性,并确保在不同的姿势中保持一致的语义身份.
主要方法:
- 开发了一个多层次的分数顺序的Gabor频率感知网络,用于准确地提取和重建高频纹理特征.
- 实现了一个全球语义-姿势对齐模块,使用交叉模式的注意力来映射姿势特征到外观语义.
- 将这些模块集成到基于扩散的生成框架中.
主要成果:
- 拟议的框架有效地重建高频纹理细节,如头发丝和织物纹.
- 在复杂的姿势变化和大角度旋转下保持结构完整性和自然纹理方面取得了卓越的性能.
- 通过SSIM,FID和感知质量指标验证的DeepFashion和Market1501数据集展示了最先进的结果.
结论:
- 拟议的基于扩散的框架显著提高了姿势引导人形图像生成中的纹理忠实性和语义一致性.
- 频率意识和全球语义对齐的整合有效地克服了以前方法的局限性.
- 该方法显示了在各种姿势中实现现实和一致的人类图像合成的巨大潜力.
相关概念视频
01:26Linear Approximation in Frequency Domain
407
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
407
01:21Association Areas of the Cortex
10.0K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
10.0K