Coherent Mark‐based Stylization of 3D Scenes at the Compositing Stage

Photorealistic image style transfer aims to transfer style information while preserving the realistic details of the content image. However, an existing limitation is the inability to effectively balance the relationship between image realism and stylization intensity, resulting in poor image transfer performance. To address this issue, we propose an photorealistic style transfer method that fusing Frequency Separation Channel Attention Mechanism (FSCAM) and Mirror Fluid Pyramid Integration (MFPI). This method achieves superior stylization intensity while improves image realism. Firstly, we propose an improved channel attention mechanism called FSCAM. This mechanism utilizes Discrete Cosine Transform (DCT) to decompose features into different frequency components and screens out high-valued texture and color features, thereby enhancing the stylization intensity of the generated images. In addition, we designed a MFPI module. The module is able to integrate information from different scales, enhance the preservation of low-level detail features in high-level features, and thus improve the realism of the images. Experimental results demonstrate that our method not only enhances the stylization intensity but also improves the image realism. It achieves satisfactory performance in terms of subjective visual performance and objective evaluation metrics.

show abstract

Coherent Mark‐based Stylization of 3D Scenes at the Compositing Stage

Abstract: Brush mask Color map Orientation map Anchor point Splat Stipple mask Color map Density map Stippling styleFigure 1: Thanks to our real-time and temporally coherent anchor point generation process, we produce a wide range of styles using different control maps and splats.

Cited by 2 publications

References 34 publications

Application of 3D Scene Fusion in Transmission Line Video Monitoring

Application of 3D Scene Fusion in Transmission Line Video Monitoring

RETRACTED: Photorealistic style transfer fusing frequency separation channel attention mechanism and mirror flow pyramid integration

Contact Info

Product

Resources

About