MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

Unsigned Distance Fields (UDFs) can be used to represent non-watertight surfaces. However, current approaches converting them into explicit meshes tend either expensive or degrade the accuracy. Here, we extend marching cube algorithm handle UDFs, both fast and accurately. Moreover, our approach surface extraction is differentiable, which key using pretrained UDF networks fit sparse data.