S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

arXiv:2403.06205v1 Announce Type: new
Abstract: Current 3D stylization methods often assume static scenes, which violates the dynamic nature of our real world. To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields. However, stylizing dynamic 3D scenes is inherently challenging due to the limited availability of stylized reference images along the temporal axis. Our key insight lies in introducing additional temporal cues besides the provided reference. To this end, we generate temporal pseudo-references …

3d scenes abstract arxiv availability cs.cv current dynamic fields however nature neural radiance fields reference temporal type world