- Updated ONNX Runtime to 1.24.4 and replaced OpenCV with PyAV 17.0.0 in the installation environment.
- Enhanced model downloading logic to prioritize Hugging Face and fallback to OmooLab R2, with improved error handling and status reporting.
- Introduced a new environment revision file for shared metadata.
- Refactored video frame extraction to utilize the PyAV library instead of OpenCV.
- Improved installation process to handle retries across specified PyPI indexes.
- Added tests for download progress reporting and model downloading behavior.
- Added `ben2_onnx.py` for BEN2 ONNX inference with preprocessing.
- Introduced `da3_onnx.py` for Depth Anything 3 inference, including camera projection calculations.
- Created `moge_onnx.py` for MoGe-2 ONNX inference and post-processing.
- Implemented shared ONNX Runtime session helpers in `onnx_runtime.py`.
- Added model synchronization script `sync_models.py` for downloading and verifying ONNX models.
- Developed unit tests for BEN2, Depth Anything 3, and MoGe ONNX models to ensure functionality.
- Updated `vendor.lock.toml` to remove unused artifacts.
- Created development.md for development setup and licensing information.
- Added features.md detailing functionalities and usage instructions for developers and users.
- Introduced index.md to serve as a navigation hub for the documentation.
- Developed outputs.md to explain output formats and their specifications.
- Established service.md to describe the AI Service architecture and environment setup.
- Created surface.md to outline the process of converting Image Empty to perspective meshes.
