Fit and independently validate rigid scan alignment from named, source traceable correspondences.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use for aligning captures or references to existing fixed geometry. Fit one rigid transform from distributed shared opaque surfaces and landmarks, with explicit fit and withheld check roles. Report all and inlier residuals, holdout residuals, scale policy, source frame/pixel provenance, and unresolved regions. Independent checks must not tune the fit.
Use planar and right angle constraints only where supported. Do not bend rooms, move levels independently, or absorb drift into plausible walls. Read formats.md and evidence-workflow.md.
Use scripts/register.py for paired landmarks with known source and target coordinates. Its transform is source-to-target, rigid, metre scale; it does not automatically certify acceptance. Identify each match visually from fixed details. Color alone, a repeated tile pattern or furniture position does not establish correspondence.
When native camera records declare tracking segments, record the accepted transform scope as exact (capture_id, tracking_segment) pairs. Before placement or reprojection, require the source frame's capture and tracking segment to match one accepted pair; reject missing or mismatched scope before applying the matrix. A frame outside that scope may still support source-local appearance or census observations when the record makes no placement claim. Register and accept the other scope separately before using it for metric placement.
Distribute fitting constraints across position and orientation, then check separate frames/features at both ends of the proposed connection. Compare planes over actual overlap rather than extrapolating tilted planes across a room. Report a regional transform if only part of a long scan passes. Keep a room adjacency/level check so a visually tidy plan cannot hide an incorrect junction.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Build and review evidence tagged Blender architectural candidates, preserve unrelated scene content, and produce requested photographic materials, stills and portable model deliveries.
The English summary is being prepared. Showing the original description.
Inspect native RGB, depth, confidence, calibration, and poses to make finite, source traceable reference points and surface measurements.
The English summary is being prepared. Showing the original description.
Preserve and inventory scan archives while retaining capture variants, hashes, calibration, and frame provenance.
The English summary is being prepared. Showing the original description.
Coordinate evidence based reconstruction from scans, photos, plans, and measurements into a reviewable Blender architectural model, with photographic appearance, renders and portable browser delivery when requested.
The English summary is being prepared. Showing the original description.
Use when cataloging or annotating visible construction in photographs or scan RGB, especially before registration or while the base model may be replaced.
The English summary is being prepared. Showing the original description.
Collect and verify Google Street View exterior references for a building reconstruction, preserving panorama identity, imagery dates, attribution and viewpoint separately from calibrated scan evidence.
The English summary is being prepared. Showing the original description.