bilateral_filter_depth — 3D depth_denoise op

• Data kinds: depth → depth

• Call: import depth_bilateral; depth_bilateral.bilateral_filter_depth(depth: 'np.ndarray', spatial_sigma: 'float', range_sigma: 'float', *, invalid: 'float | None' = 0.0, truncate: 'float' = 3.0) -> 'np.ndarray' (or ops3d.get("bilateral_filter_depth"))

Usage

A bilateral filter for depth images (edge-preserving denoising). → float64 (H,W).

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)

• depth_denoise — py -3.11 examples_3d/depth_denoise.py

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

depth_to_points · tsdf_from_depth · to_points · fuse_to_voxel · depth_to_organized_points · normals_from_depth · occlusion_edges · bearing_angle_image

Same category (depth_denoise)

joint_bilateral · fill_holes

*Provenance: depth_bilateral.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.