domain op• Data kinds: voxel × voxel → voxel
• Call: import fullseye as fs; fs.ledger.vol_reduce_domain(vol, domain) (to call the implementation directly, import volops; volops.vol_reduce_domain(vol, domain); from the registry, ops3d.get("vol_reduce_domain"))
Restrict a volume to a *domain* mask (HALCON `reduce_domain`, voxel-wise).
Every voxel outside the foreground of *domain* is set to `0` — the same
"outside the domain is undefined -> 0" convention the 2-D `it_crop_domain`
op uses (a plain numpy array cannot carry a separate domain channel, so the
restriction is materialised). A non-`{0, 1}` *domain* is thresholded at
`> 0.5`. Use it to silence everything a downstream operator must not see
(metal artefacts, the scanner bed, a neighbouring part); combine with
:func:vol_crop_domain when you also want the *memory* of the volume
reduced, not just its values.
Returns a `(D, H, W)` float64 volume of the same shape.
• 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.
• roi_domain_boundary — py -3.11 examples_3d/roi_domain_boundary.py
voxel as input)voxel_to_mips · voxel_to_mesh · signed_distance_field · to_points · sobel3d · hessian3d · curvature_maps · edt_jfa
domain)vol_bounding_box · vol_crop_domain · vol_uncrop · vol_tiled_map
*Provenance: volops.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.