Skip to content

Open3D ICP demo: three indoor point-cloud fragments

pl.load("open3d_icp_demo") loads this dataset. The point clouds of Open3D registration tutorials (RGB-D reconstruction fragments). Pairs for RANSAC + ICP.

import pardesline as pl

ds = pl.load("open3d_icp_demo")
print(ds.describe())  # roles, frames, units, labels, licence, citation
s = ds[0]
obj = s.source  # fetched now, cached under ~/.cache/pardesline/datasets/open3d_icp_demo

Provenance and licence
Source open3d.data demo download
Scheme open3d
Size of the whole source 6 MB
Licence not a standard licence: see the note
Redistribution unknown
Licence note Redwood indoor RGB-D dataset fragments distributed by Open3D. Terms TO CONFIRM.
Terms http://redwood-data.org/indoor/
Cite Choi S., Zhou Q.-Y., Koltun V. Robust reconstruction of indoor scenes. CVPR 2015.
Samples grouped by scene
Samples listed in the manifest 2

Roles (what each sample contains)

Role Type Frame Units Labels / layout Pattern or file
source points sensor m cloud_bin_0.pcd, cloud_bin_1.pcd
Fragment to align (moving)
target points sensor m cloud_bin_1.pcd, cloud_bin_2.pcd
Reference fragment (fixed)

Standardized layout

Files are fetched on first access into the dataset cache and stay in their original format; ds.export(folder) writes every sample as standard files (PLY for points and meshes, MetaImage for volumes and label maps) with a .pardesline.json sidecar carrying frame, units, labels, licence and provenance, plus a manifest for the folder. Label maps become exact surfaces with to_mesh(label=k), DICOM series become one volume, raw arrays are decoded through the layout above.

ds = pl.load("open3d_icp_demo").take(2)
ds.export("./standardized")        # PLY / MetaImage + sidecars + manifest.json

Algorithms and models that run on it

Generated from src/pardesline/data/manifests/open3d_icp_demo.json on 2026-10-10.