StyleTRF: Stylizing Tensorial Radiance Fields
This work addresses the need for efficient stylized view generation in computer vision, though it appears incremental as it builds on existing TensoRF and stylization techniques.
The paper tackles the problem of generating stylized views from casually captured scenes by introducing StyleTRF, a method that decouples style adaptation from view capture using TensoRF representation, achieving faster training times than previous approaches.
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.