Efficient 3D Instance Mapping and Localization with Neural Fields

arXiv:2403.19797v1 Announce Type: new
Abstract: We tackle the problem of learning an implicit scene representation for 3D instance segmentation from a sequence of posed RGB images. Towards this, we introduce 3DIML, a novel framework that efficiently learns a label field that may be rendered from novel viewpoints to produce view-consistent instance segmentation masks. 3DIML significantly improves upon training and inference runtimes of existing implicit scene representation based methods. Opposed to prior art that optimizes a neural field in a self-supervised …

abstract arxiv consistent cs.cv fields framework images instance localization mapping novel representation segmentation type view