Stylized view generation of scenes captured casually using a camera has received much attention recently. The geometry and appearance of the scene are typically captured as neural point sets or neural radiance fields in the previous work. An image stylization method is used to stylize the captured appearance by training its network jointly or iteratively with the structure capture network. The state-of-the-art SNeRF method trains the NeRF and stylization network in an alternating manner. These methods have high training time and require joint optimization. In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF. The appearance part is fine-tuned using sparse stylized priors of a few views rendered using the TensoRF representation for a few iterations. Our method thus effectively decouples style-adaption from view capture and is much faster than the previous methods. We show state-of-the-art results on several scenes used for this purpose.
翻译:使用相机偶然拍摄的场景的同步生成方式最近受到了很多关注。 场景的几何和外观通常作为神经点集或神经光亮场在先前的工作中被捕捉。 图像元化方法用于通过联合培训网络或与结构捕捉网络迭接来将所捕捉的场景进行发星体化。 最新先进的SNERF方法以交替方式对NERF和Styl化网络进行培训。 这些方法具有很高的培训时间,需要联合优化。 在这项工作中, 我们展示StyleTRF, 一种紧凑的、 快速优化战略, 用于使用 TensoRF 生成的闪光化视图。 外观部分使用微小的星化前端, 使用 TensoRF 表达方式对少数视图进行微调。 因此,我们的方法能够有效地将NERF和Syldal化网络从视图捕捉取中分离出来, 并且比以往方法要快得多。 我们展示了用于此目的的若干场景的状态结果。