ViFu: Multiple 360$^\circ$ Objects Reconstruction with Clean Background via Visible Part Fusion

arXiv:2404.09426v1 Announce Type: new
Abstract: In this paper, we propose a method to segment and recover a static, clean background and multiple 360$^\circ$ objects from observations of scenes at different timestamps. Recent works have used neural radiance fields to model 3D scenes and improved the quality of novel view synthesis, while few studies have focused on modeling the invisible or occluded parts of the training images. These under-reconstruction parts constrain both scene editing and rendering view selection, thereby limiting their …

3d scenes abstract arxiv cs.cv fields fusion multiple neural radiance fields novel objects paper part quality segment type via