DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

arXiv:1905.10711v5 Announce Type: replace
Abstract: Reconstructing 3D shapes from single-view images has been a long-standing research problem. In this paper, we present DISN, a Deep Implicit Surface Network which can generate a high-quality detail-rich 3D mesh from an 2D image by predicting the underlying signed distance fields. In addition to utilizing global image features, DISN predicts the projected location for each 3D point on the 2D image, and extracts local features from the image feature maps. Combining global and local …

3d reconstruction arxiv cs.cv network quality surface type view