Modeling 3D Surface Manifolds with a Locally Conditioned Atlas

TL;DR

This paper introduces LoCondA, a hierarchical generative framework that improves 3D surface reconstruction by maintaining local consistency across patches, resulting in higher quality, topologically diverse meshes.

Contribution

The novel Locally Conditioned Atlas (LoCondA) framework enforces local consistency in 3D mesh generation, addressing discontinuities in patch-based reconstructions.

Findings

Produces structurally coherent 3D meshes

Maintains local patch consistency

Generates topologically diverse objects

Abstract

Recently proposed 3D object reconstruction methods represent a mesh with an atlas - a set of planar patches approximating the surface. However, their application in a real-world scenario is limited since the surfaces of reconstructed objects contain discontinuities, which degrades the quality of the final mesh. This is mainly caused by independent processing of individual patches, and in this work, we postulate to mitigate this limitation by preserving local consistency around patch vertices. To that end, we introduce a Locally Conditioned Atlas (LoCondA), a framework for representing a 3D object hierarchically in a generative model. Firstly, the model maps a point cloud of an object into a sphere. Secondly, by leveraging a spherical prior, we enforce the mapping to be locally consistent on the sphere and on the target object. This way, we can sample a mesh quad on that sphere and project it back onto the object's manifold. With LoCondA, we can produce topologically diverse objects while maintaining quads to be stitched together. We show that the proposed approach provides structurally coherent reconstructions while producing meshes of quality comparable to the competitors.