all AI news
SSR-2D: Semantic 3D Scene Reconstruction from 2D Images. (arXiv:2302.03640v3 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Most deep learning approaches to comprehensive semantic modeling of 3D indoor
spaces require costly dense annotations in the 3D domain. In this work, we
explore a central 3D scene modeling task, namely, semantic scene reconstruction
without using any 3D annotations. The key idea of our approach is to design a
trainable model that employs both incomplete 3D reconstructions and their
corresponding source RGB-D images, fusing cross-domain features into volumetric
embeddings to predict complete 3D geometry, color, and semantics with only …
annotations arxiv color deep learning design features generated geometry images labeling machine modeling semantic semantic modeling semantics spaces the key work