{"ID":2895519,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08223","arxiv_id":"2507.08223","title":"SurfDist: Interpretable Three-Dimensional Instance Segmentation Using Curved Surface Patches","abstract":"We present SurfDist, a convolutional neural network architecture for three-dimensional volumetric instance segmentation. SurfDist enables prediction of instances represented as closed surfaces composed of smooth parametric surface patches, specifically bicubic Bézier triangles. SurfDist is a modification of the popular model architecture StarDist-3D which breaks StarDist-3D's coupling of instance parameterization dimension and instance voxel resolution, and it produces predictions which may be upsampled to arbitrarily high resolutions without introduction of voxelization artifacts. For datasets with blob-shaped instances, common in biomedical imaging, SurfDist can outperform StarDist-3D with more compact instance parameterizations. We detail SurfDist's technical implementation and show one synthetic and one real-world dataset for which it outperforms StarDist-3D. These results demonstrate that interpretable instance surface models can be learned effectively alongside instance membership.","short_abstract":"We present SurfDist, a convolutional neural network architecture for three-dimensional volumetric instance segmentation. SurfDist enables prediction of instances represented as closed surfaces composed of smooth parametric surface patches, specifically bicubic Bézier triangles. SurfDist is a modification of the popular...","url_abs":"https://arxiv.org/abs/2507.08223","url_pdf":"https://arxiv.org/pdf/2507.08223v2","authors":"[\"Jackson Borchardt\",\"Saul Kato\"]","published":"2025-07-11T00:03:55Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}