High Resolution UDF Meshing via Iterative Networks
This addresses a domain-specific challenge in 3D reconstruction for applications like computer graphics and simulation, offering an incremental improvement over single-pass methods by enhancing surface recovery in noisy UDFs.
The paper tackles the problem of triangulating Unsigned Distance Fields (UDFs) into explicit meshes at high resolutions, where noise and ambiguity cause missing surfaces and holes, by introducing an iterative neural network that propagates neighborhood information across multiple passes to correct errors and stabilize extraction, resulting in significantly more accurate and complete meshes than existing approaches.
Unsigned Distance Fields (UDFs) are a natural implicit representation for open surfaces but, unlike Signed Distance Fields (SDFs), are challenging to triangulate into explicit meshes. This is especially true at high resolutions where neural UDFs exhibit higher noise levels, which makes it hard to capture fine details. Most current techniques perform within single voxels without reference to their neighborhood, resulting in missing surface and holes where the UDF is ambiguous or noisy. We show that this can be remedied by performing several passes and by reasoning on previously extracted surface elements to incorporate neighborhood information. Our key contribution is an iterative neural network that does this and progressively improves surface recovery within each voxel by spatially propagating information from increasingly distant neighbors. Unlike single-pass methods, our approach integrates newly detected surfaces, distance values, and gradients across multiple iterations, effectively correcting errors and stabilizing extraction in challenging regions. Experiments on diverse 3D models demonstrate that our method produces significantly more accurate and complete meshes than existing approaches, particularly for complex geometries, enabling UDF surface extraction at higher resolutions where traditional methods fail.