CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections

TL;DR

CrossSDF is a new neural method that accurately reconstructs thin 3D structures from 2D cross-sectional data, overcoming limitations of existing techniques in medical imaging and related fields.

Contribution

It introduces a contour-aware neural SDF approach that improves reconstruction of thin and complex structures from planar slices.

Findings

Significantly better reconstruction of thin structures.

Reduces artifacts and over-smoothing compared to prior methods.

Effective in medical imaging applications.

Abstract

Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography. Out-of-the-box point cloud reconstruction methods can often fail due to the data sparsity between slicing planes, while current bespoke methods struggle to reconstruct thin geometric structures and preserve topological continuity. This is important for medical applications where thin vessel structures are present in CT and MRI scans. This paper introduces CrossSDF, a novel approach for extracting a 3D signed distance field from 2D signed distances generated from planar contours. Our approach makes the training of neural SDFs contour-aware by using losses designed for the case where geometry is known within 2D slices. Our results demonstrate a significant improvement over existing methods, effectively reconstructing thin structures and producing accurate 3D models without the interpolation artifacts or over-smoothing of prior approaches.