sobel3d — 3D feature op

• Data kinds: voxel → gradient

• Call: import match3d; match3d.sobel3d(vol, device='cpu') (or ops3d.get("sobel3d"))

• GPU: this op has a GPU path (device="cuda")

Usage

The 3-D gradient (gz, gy, gx). Separable conv3d of the derivative [-1,0,1] × the smoother [1,2,1].

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

Runnable examples (verified samples that actually call this op)

• diff_features — py -3.11 examples_3d/diff_features.py

Ops the type connects to (they accept gradient as input)

fuse_to_voxel

Same category (feature)

hessian3d · curvature_maps · edt_jfa · vol_frangi · vol_sato · vol_hessian_blobness · vol_gradient_magnitude · vol_local_maxima

*Provenance: match3d.py — 3D operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.