Calibrex 0.4.1 — LiDAR-camera evidence in five minutes

Calibrex 0.4.1 — know whether your LiDAR-camera calibration is trustworthy

Calibrex 0.4.1 turns the first LiDAR-camera experience into a no-download, ROS-independent evidence workflow. Install the wheel, run the strict demo, inspect the HTML report, and verify the digest-bound provenance bundle:

python -m pip install \
  "https://github.com/rsasaki0109/Calibrex/releases/download/v0.4.1/calibrex-0.4.1-py3-none-any.whl"

calibrex demo kitti-lidar-camera-evidence \
  --output-dir outputs/kitti-lidar-camera-evidence \
  --strict-assessment
calibrex validate outputs/kitti-lidar-camera-evidence/result.yaml
calibrex verify outputs/kitti-lidar-camera-evidence/bundle.json \
  --require-raw-recomputed

What the demo proves

• The wheel contains a deterministic, generator-bound KITTI-shaped Camera-LiDAR fixture; no ROS installation or dataset download is required.
• The reference projection detects 16 of 24 mandatory ±1 degree / ±0.10 m known-bad perturbation cases.
• All six falsification-policy gates pass without relaxed thresholds.
• The result, report artifacts, input files, and assessment are connected through schema-valid, SHA-256-bound provenance.
• The clean Windows wheel path completes in under one minute; the same wheel smoke passes in GitHub Actions on Python 3.10, 3.11, and 3.12.

The bundled fixture verifies Calibrex's evaluation and evidence contracts. It is intentionally synthetic and is not a physical-rig accuracy claim or a standalone LiDAR-camera calibration algorithm. Use --dataset-path with an officially downloaded KITTI raw sequence when evaluating real data.

Other changes since 0.4.0

• Camera-LiDAR SOTA audit and research pipelines with digest-frozen protocols.
• Evidence-first solid-state LiDAR workflows, public-data gates, and real calibration visualizations.
• Calibration CI, schema, adapter, and provenance improvements accumulated on main.

See CHANGELOG.md and the full comparison.

Release verification

• Release workflow and isolated wheel smoke: passed.
• Main CI: all Python 3.10/3.11/3.12 test, lint, type-check, schema, and wheel-smoke jobs passed.
• Documentation build and GitHub Pages deployment: passed.
• Wheel SHA-256: 29888b11596e748ea1f211112bca50cf66e9822593b47b8fa2dd2648297cb55e
• Source distribution SHA-256: 093760324b616560a041af675c418e863fb94eadade7b39d00944822ed79b498

v0.4.0

Calibration evidence, not just a matrix. Review CHANGELOG.md, wheel smoke results, license boundaries, and public dataset notes before publishing this draft.

What's Changed

• [codex] Add online calibration README hero GIF by @rsasaki0109 in #1
• [codex] Document online calibration GIF generation by @rsasaki0109 in #3
• [codex] Validate README GIF visual modes by @rsasaki0109 in #4
• [codex] Version README GIF manifest visual schema by @rsasaki0109 in #5
• [codex] Schema validate README GIF manifest by @rsasaki0109 in #6
• Fix CI schema count and complete alpha changelog by @rsasaki0109 in #7
• Scope alpha claims to LiDAR-main evaluation by @rsasaki0109 in #8
• Make public-dataset frame sampling configurable by @rsasaki0109 in #9
• Add N-way report-compare command with schema by @rsasaki0109 in #10
• Add pure-Python rosbag1 reader and TIERS LidarsCali demo by @rsasaki0109 in #11
• Fix CI mypy step to avoid numpy stub parsing failure by @rsasaki0109 in #13
• Wire native LiDAR point-to-plane solver into the calibrate pipeline by @rsasaki0109 in #12
• Document PR #9-#12 features in the alpha changelog by @rsasaki0109 in #14
• Add KITTI camera-LiDAR evidence demo by @rsasaki0109 in #15
• Publish docs/ as an MkDocs Material site by @rsasaki0109 in #16
• Add online/streaming LiDAR calibration (calibrate --online) by @rsasaki0109 in #17
• Implement nuScenes radar velocity-consistency metric by @rsasaki0109 in #19
• Drive online README GIF from real calibrate --online timeline by @rsasaki0109 in #18
• Add multi-batch observation accumulation for online calibration by @rsasaki0109 in #20
• Wire rosbag1 Livox streams into online LiDAR-pair calibration by @rsasaki0109 in #21
• README hero GIF: TIERS solid-state Livox online calibration by @rsasaki0109 in #22
• Validate spinning×solid-state online calibration on TIERS LidarsCali by @rsasaki0109 in #23
• Render online calibration timeline in HTML report by @rsasaki0109 in #24
• ADR 0005: v0.2 motion, camera, and temporal direction by @rsasaki0109 in #25
• Add pure-Python rosbag2 reader (sqlite3 + MCAP) by @rsasaki0109 in #26
• Add odometry-aware rosbag2 online motion compensation by @rsasaki0109 in #27
• Validate odometry-aware online calibration on TIERS Indoor02 real data by @rsasaki0109 in #28
• Add KISS-ICP rig-frame odometry for TIERS Indoor02 validation by @rsasaki0109 in #29
• Per-point deskew for rosbag2 online motion compensation by @rsasaki0109 in #30
• Promote camera-LiDAR projection to evaluated evidence (ADR 0005 Pillar 2) by @rsasaki0109 in #31
• Rename Calibrex to slac (breaking) by @rsasaki0109 in #32
• Add temporal time-offset evidence to online motion-compensated calibration by @rsasaki0109 in #33
• Docs: close out ADR 0005 v0.2 acceptance evidence by @rsasaki0109 in #34
• Add ADR 0007: v0.3 SLAC direction by @rsasaki0109 in #35
• README hero: TIERS Indoor02 motion SLAC loop GIF by @rsasaki0109 in #36
• Skip GIF text-bake test without ffmpeg/fontconfig by @rsasaki0109 in #37
• Trajectory artifact and ground-truth-free quality gates (ADR 0007 Pillar 1) by @rsasaki0109 in #38
• Two-pass and native-deskew KISS-ICP odometry (ADR 0007 Pillar 1) by @rsasaki0109 in #39
• Anchored temporal evidence and joint separability (ADR 0007 Pillar 2) by @rsasaki0109 in #40
• LiDAR-IMU rotation evidence (ADR 0007 Pillar 3) by @rsasaki0109 in #41
• Docs: close out ADR 0007 v0.3 acceptance evidence by @rsasaki0109 in #42
• Docs: ADR 0008 v0.4 direction — full-scale modality PASS and absolute time by @rsasaki0109 in #43
• Restore Calibrex and expand calibration methods by @rsasaki0109 in #44
• Update canonical repository URLs by @rsasaki0109 in #45
• Polish README evidence visuals by @rsasaki0109 in #46
• Document development roadmap by @rsasaki0109 in #47
• Prepare Calibrex public launch by @rsasaki0109 in #48
• Move calibration coverage near quickstart by @rsasaki0109 in #49
• Add ETHZ real-data benchmark table by @rsasaki0109 in #50
• Add reproducible N-way benchmark foundation by @rsasaki0109 in #51
• Complete v0.4 adoption track by @rsasaki0109 in #52

New Contributors

• @rsasaki0109 made their first contribution in #1

Full Changelog: https://github.com/rsasaki0109/Calibrex/commits/v0.4.0