Files
AnyImage/docs/outputs.md
nan 2ad30bf4a3 feat: Implement ONNX model inference for BEN2, Depth Anything 3, and MoGe
- 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.
2026-08-14 10:27:09 +08:00

1.1 KiB
Raw Blame History

输出格式

DA3 ONNX

Output Type 提供以下结果:

  • Point Cloud (GLB):由 depth、confidence、相机参数和原图生成彩色点云
  • Depth Preview (Images):保存深度着色预览
  • Depth Data (NPZ):保存 depth、confidence、extrinsics、intrinsics 与处理后的图像
  • Textured Surface (GLB):SnapForm 根据 Prediction 构建纹理网格

DA3 Small 与 Base 的 ONNX 图不包含 Gaussian head,因此不提供 Gaussian Splats。默认推理参数为:

  • process_res=504
  • process_res_method="upper_bound_resize"
  • ref_view_strategy="saddle_balanced"
  • conf_thresh_percentile=40.0
  • num_max_points=1_000_000
  • show_cameras=True

相机外参与内参由模型的 camera decoder 输出恢复,不运行 ray-pose 求解器。

MoGe-2 ONNX

MoGe-2 Debug 可保存原始 NPZ、depth/normal/mask maps、纹理 GLB 或彩色 PLY。Surface 输出由模型 points、mask 与 depth edge 在内部构建三角网格。

BEN2 ONNX

BEN2 输出 foreground.png,RGB 保留原始输入,Alpha 来自 ONNX mask 并恢复到输入分辨率。