Photorealistic stylization of 3D scenes aims to generate photorealistic images from arbitrary novel views according to a given style image, while ensuring consistency when rendering video from different viewpoints. Some existing stylization methods using neural radiance fields can effectively predict stylized scenes by combining the features of the style image with multi-view images to train 3D scenes. However, these methods generate novel view images that contain undesirable artifacts. In addition, they cannot achieve universal photorealistic stylization for a 3D scene. Therefore, a stylization image needs to retrain a 3D scene representation network based on a neural radiation field. We propose a novel photorealistic 3D scene stylization transfer framework to address these issues. It can realize photorealistic 3D scene style transfer with a 2D style image for novel view video rendering. We first pre-trained a 2D photorealistic style transfer network, which can satisfy the photorealistic style transfer between any content image and style image. Then, we use voxel features to optimize a 3D scene and obtain the geometric representation of the scene. Finally, we jointly optimize a hypernetwork to realize the photorealistic style transfer of arbitrary style images. In the transfer stage, we use a pre-trained 2D photorealistic network to constrain the photorealistic style of different views and different style images in the 3D scene. The experimental results show that our method not only realizes the 3D photorealistic style transfer of arbitrary style images, but also outperforms the existing methods in terms of visual quality and consistency.

Knowledge distillation has been widely applied in semantic segmentation to reduce the model size and computational complexity. The prior knowledge distillation methods for semantic segmentation mainly focus on transferring the spatial relation knowledge, neglecting to transfer the channel correlation knowledge in the feature space, which is vital for semantic segmentation. We propose a novel Channel Correlation Distillation (CCD) method for semantic segmentation to solve this issue. The correlation between channels tells how likely these channels belong to the same categories. We force the student to mimic the teacher by minimizing the distance between the channel correlation maps of the student and the teacher. Furthermore, we propose the multi-scale discriminators to sufficiently distinguish the multi-scale differences between the teacher and student segmentation outputs. Extensive experiments on three popular datasets: Cityscapes, CamVid, and Pascal VOC 2012 validate the superiority of our CCD. Experimental results show that our CCD could consistently improve the state-of-the-art methods with various network structures for semantic segmentation.