Topologically-Aware Deformation Fields for Single-View 3D Reconstruction. (arXiv:2205.06267v1 [cs.CV])

We present a new framework for learning 3D object shapes and dense
cross-object 3D correspondences from just an unaligned category-specific image
collection. The 3D shapes are generated implicitly as deformations to a
category-specific signed distance field and are learned in an unsupervised
manner solely from unaligned image collections without any 3D supervision.
Generally, image collections on the internet contain several intra-category
geometric and topological variations, for example, different chairs can have
different topologies, which makes the task of joint shape …

3d 3d reconstruction arxiv cv