- Extract apply_depth_verify_refine_postprocess() from main() for testability
- Add test_depth_cli_postprocess.py using mocks to validate JSON and CSV behavior
- Keeps CLI behavior unchanged
- Ensure default extrinsics calibration runs with depth mode NONE
- Depth is only enabled when --verify-depth or --refine-depth is set
- Document opt-in behavior in notepad
- Retrieve depth + confidence measures from SVOReader when depth enabled
- Compute depth residual metrics and attach to output JSON
- Optionally write per-corner residual CSV via --report-csv
- Post-process refinement: optimize final pose and report pre/post metrics
- Add unit tests for depth verification and refinement modules
- Add basedpyright dev dependency for diagnostics
- Add DepthVerificationResult dataclass for metrics
- Add project_point_to_pixel() for 3D to 2D projection
- Add compute_depth_residual() with median window sampling
- Add verify_extrinsics_with_depth() for batch verification
- Support confidence-based filtering
- Add optional dist parameter to match test expectations
- Handle single-point case where squeeze() removes necessary dimension
- Fixes failing tests in test_pose_math.py
- Add comprehensive work plan for ArUco-based multi-camera calibration
- Add recording_multi.py for multi-camera SVO recording
- Add streaming_receiver.py for network streaming
- Add svo_playback.py for synchronized playback
- Add zed_network_utils.py for camera configuration
- Add AGENTS.md with project context
- Implemented a new sample application in main.cpp to capture and display a live 3D point cloud using the ZED SDK and OpenGL.
- Created test_opengl.cpp to demonstrate basic OpenGL rendering with depth testing using two triangles.
- Added test_points.cpp to visualize a grid of colored points in OpenGL, showcasing point rendering capabilities.
crosstyan