refine_translation_lk — 3D refine op

• Data kinds: voxel × voxel × position → position

• Call: import match3d; match3d.refine_translation_lk(scene, template, init_pos, device='cpu', iters=30, tol=0.0001) (or ops3d.get("refine_translation_lk"))

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

Usage

Sub-voxel refinement of the 3-D translation by inverse-compositional Lucas-Kanade with Gauss-Newton.

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)

• refinement — py -3.11 examples_3d/refinement.py

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

refine_peak_newton · refine_lm · fuse_to_voxel

Same category (refine)

refine_peak_newton · refine_lm · refine_rotation_z · icp_point2point_3d · icp_point2plane

*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.