GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fields
This addresses the challenge of coherent stylization for dynamic 3D scenes, which is incremental as it builds on existing radiance field methods by adding geometry-aware capabilities.
The paper tackled the problem of 3D stylization in dynamic scenes by proposing GAS-NeRF, which jointly transfers appearance and geometry details, resulting in enhanced stylization quality and maintained temporal coherence in experiments on synthetic and real-world datasets.
Current 3D stylization techniques primarily focus on static scenes, while our world is inherently dynamic, filled with moving objects and changing environments. Existing style transfer methods primarily target appearance -- such as color and texture transformation -- but often neglect the geometric characteristics of the style image, which are crucial for achieving a complete and coherent stylization effect. To overcome these shortcomings, we propose GAS-NeRF, a novel approach for joint appearance and geometry stylization in dynamic Radiance Fields. Our method leverages depth maps to extract and transfer geometric details into the radiance field, followed by appearance transfer. Experimental results on synthetic and real-world datasets demonstrate that our approach significantly enhances the stylization quality while maintaining temporal coherence in dynamic scenes.