normals_from_depth — 3D `range_image` op

• Data kinds: depth → normalmap

• Call: import range_image; range_image.normals_from_depth(depth, fx=None, fy=None, cx=None, cy=None, orient_to_camera=True) (or ops3d.get("normals_from_depth"))

Usage

Organized depth → oriented unit normals (H,W,3). The cross product of the 3-D points of neighbouring pixels (using the grid structure, O(HW)).

Background guides (the physics and conventions behind this op)

• blender_interop — Blender との併用 — 形を作って fullseye で測る(軸・単位・正解データの罠)

• depth_sensors — 深度センサの知識 — 測距原理・実機の値・欠測の出方

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)

• range_image — py -3.11 examples_3d/range_image.py

Ops the type connects to (they accept `normalmap` as input)

fuse_to_voxel · render_shaded · phong_shade · matcap_shade · brdf_lommel_seeliger · brdf_hapke · bump_normals_fbm · integrate_normals

Same category (`range_image`)

depth_to_organized_points · occlusion_edges · bearing_angle_image

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

normals_from_depth — 3D range_image op