crosstyan/zed-playground
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Implement FPFH+RANSAC global pre-alignment (Task 6)

Browse Source
This commit is contained in:
crosstyan
2026-02-10 16:24:59 +00:00
parent 1d2e66a34c
commit 2c93c77db8
3 changed files with 181 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py_workspace/.sisyphus/notepads/full-icp-pipeline/learnings.md
+16
View File
@@ -25,3 +25,19 @@
- Verified hybrid mode behavior (vertical structure inclusion and fallback).
- Verified full mode behavior.
- Verified SOR preprocessing effectiveness.
## Task 4: TukeyLoss Robust Kernel Support
- Added `robust_kernel` and `robust_kernel_k` to `ICPConfig`.
- Implemented TukeyLoss application in `pairwise_icp` for both Point-to-Plane and Generalized ICP.
- Verified that TukeyLoss correctly handles outliers in synthetic tests, maintaining convergence accuracy.
- Default behavior remains backward-compatible with `robust_kernel="none"`.
## Task 6: FPFH+RANSAC Global Pre-alignment
- Implemented `compute_fpfh_features` and `global_registration` using Open3D RANSAC.
- Added `global_init` flag to `ICPConfig` (default False).
- Integrated global registration into `refine_with_icp` as a pre-alignment step before pairwise ICP.
- Added safety checks: global registration result is only used if fitness > 0.1 and the resulting transform is within `max_rotation_deg` and `max_translation_m` bounds relative to the initial extrinsic guess.
- Verified with synthetic tests:
- `test_compute_fpfh_features`: Validates feature dimension and count.
- `test_global_registration_known_transform`: Confirms RANSAC can recover a known large transform (30 deg rotation).
- `test_refine_with_icp_global_init_success`: End-to-end test showing global init can recover from a very bad initial guess (90 deg error) where local ICP would fail.