v4.1.0
chenglou/pretextv4.1.0Oct 1, 2026by github-actions[bot]
Upgrading?
AI Summary
X-AnyLabeling 4.1.0 introduces a dedicated 3D point cloud annotation workspace, expands classification workflows, and improves everyday annotation and model management.
Key Highlights
- Add 3D point cloud semantic and instance segmentation with brush and polygon selection.
- Integrate classification model predictions as image flags.
- Add a collapsible sidebar with bounded resizing.
- Allow downloaded model files to be deleted from the model dropdown.
Breaking Changes
- Remove the broken standalone converter entry point.
New Features
- 3D point cloud semantic and instance segmentation with brush and polygon selection.
- 3D object detection annotation with editable cuboids and multi-camera support.
- Classification model predictions as image flags.
- Collapsible sidebar with bounded resizing.
- Localized, searchable keyboard shortcuts dialog.
- Delete downloaded model files from the model dropdown.
Full Release Notes
> PyPI: https://pypi.org/project/x-anylabeling-cvhub/ > [!NOTE] > Due to compatibility issues across different systems, if the precompiled version doesnβt work properly on your machine, you can try building and running it from source instead. For details, check out the official installation guide and user documentation. X-AnyLabeling 4.1.0 introduces a dedicated 3D point cloud annotation workspace, expands classification workflows, and improves everyday annotation and model management. ### π New Features - Add 3D point cloud semantic and instance segmentation with brush and polygon selection, class and instance management, automatic saving, and calibrated camera projection. (#162) - Add 3D object detection annotation with editable cuboids, top/side/front views, multi-camera support, and dataset import and export workflows. - Integrate classification model predictions as image flags and add searchable categories to the image classifier. (#1457) - Add a collapsible sidebar with bounded resizing. (#1357) - Add a localized, searchable keyboard shortcuts dialog. - Allow downloaded model files to be deleted from the model dropdown with localized confirmation dialogs. ### π Bug Fixes - Prevent crashes when switching drawing modes with unfinished shapes. - Fix point cloud file loading crashes on Windows. - Fix RF-DETR top-k selection boundaries and preserve empty selections. (#1450) - Remove the broken standalone converter entry point that raised a TypeError. - Preserve lazy loading of point cloud modules when adding the keyboard shortcuts dialog. ### π οΈ Improvements - Unify auto-labeling model loading while preserving static lazy imports. (#1454) - Streamline the AI panel layout and remove its redundant close button. - Expand English and Chinese point cloud guides, sample datasets, and classification documentation. - Run release tests with a virtual display and software OpenGL rendering for point cloud coverage. ### π Contributors A total of 3 developers contributed to this release. Thank @Anai-Guo, @CVHub520, @MNakahara-ishidatec **Full Changelog**: https://github.com/CVHub520/X-AnyLabeling/compare/v4.0.6...v4.1.0
Related Repositories
openclaw/openclawβ
392,696
The AI that really does things. Any OS. Any Platform. The lobster way. π¦
nilbuild/developer-roadmapβ
370,067
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/reaβ
357,700
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencodeβ
219,670
The open source coding agent.
n8n-io/n8nβ
208,251
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.