Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

arXiv:2403.18922v1 Announce Type: new
Abstract: In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets. At the same time, there has been renewed interest in 3D scene representations such as neural radiance fields from multi-view images. However, the availability of 3D or multiview data is still substantially limited compared to 2D image datasets, making extending 2D vision models to 3D …

2d image abstract arxiv cs.cv datasets editing image image datasets scale segmentation semantic style style transfer tasks transfer type vision vision models zero-shot