Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation

arXiv:2403.19319v1 Announce Type: new
Abstract: We present Mesh2NeRF, an approach to derive ground-truth radiance fields from textured meshes for 3D generation tasks. Many 3D generative approaches represent 3D scenes as radiance fields for training. Their ground-truth radiance fields are usually fitted from multi-view renderings from a large-scale synthetic 3D dataset, which often results in artifacts due to occlusions or under-fitting issues. In Mesh2NeRF, we propose an analytic solution to directly obtain ground-truth radiance fields from 3D meshes, characterizing the density …

3d scenes abstract arxiv cs.cv fields generative ground-truth mesh meshes neural radiance field representation scale supervision synthetic tasks training truth type view