Pruning-based Topology Refinement of 3D Mesh using a 2D Alpha Mask

TL;DR

This paper introduces a topology refinement method for 3D meshes using 2D alpha masks and differentiable rendering, enabling improved reconstruction without costly ground-truth data.

Contribution

It proposes a face-pruning strategy that refines 3D mesh topology via 2D soft masks, independent of the underlying reconstruction network.

Findings

Effective topology refinement using 2D alpha masks.

Compatible with various self-supervised 3D reconstruction pipelines.

Produces complex meshes with non-spherical topology.

Abstract

Image-based 3D reconstruction has increasingly stunning results over the past few years with the latest improvements in computer vision and graphics. Geometry and topology are two fundamental concepts when dealing with 3D mesh structures. But the latest often remains a side issue in the 3D mesh-based reconstruction literature. Indeed, performing per-vertex elementary displacements over a 3D sphere mesh only impacts its geometry and leaves the topological structure unchanged and fixed. Whereas few attempts propose to update the geometry and the topology, all need to lean on costly 3D ground-truth to determine the faces/edges to prune. We present in this work a method that aims to refine the topology of any 3D mesh through a face-pruning strategy that extensively relies upon 2D alpha masks and camera pose information. Our solution leverages a differentiable renderer that renders each face as a 2D soft map. Its pixel intensity reflects the probability of being covered during the rendering process by such a face. Based on the 2D soft-masks available, our method is thus able to quickly highlight all the incorrectly rendered faces for a given viewpoint. Because our module is agnostic to the network that produces the 3D mesh, it can be easily plugged into any self-supervised image-based (either synthetic or natural) 3D reconstruction pipeline to get complex meshes with a non-spherical topology.