blendcap-onnx-exports

BlendCap ONNX Exports

Pre-generated ONNX Runtime files for the BlendCap performance capture addon for Blender.

These are NOT standalone models. They're component exports (backbone, FOV encoder, and pose detector) used inside BlendCap's larger SAM 3D Body + YOLO11 + MoGe inference pipeline. You almost certainly want BlendCap itself, not these files directly. This repository is not affiliated with or endorsed by Meta, Ultralytics, or Microsoft.

Licenses — read before downloading

By downloading or using the files in this repository you accept the license terms that govern them. Each file keeps the license of the model it was exported from — see the table below; copies of every license are included in this repository. Under the Meta license's own terms (Section 6), the agreement commences upon acceptance of the agreement or access to the materials. (LICENSE_DINOV3.txt is included for reference as well, since the backbone is a DINOv3 model that Meta distributes as part of the SAM 3D Body release.)

In short: commercial use is permitted under each license, redistribution must carry the applicable license text along, and everything is provided as-is with no warranty.

Files

The backbone uses ONNX's external-data format because its weights exceed protobuf's 2 GB in-memory limit. Both backbone_dinov3_fp16.onnx and backbone_dinov3_fp16.onnx_data must be downloaded together and kept in the same directory with their exact names preserved — the .onnx file references .onnx_data by relative filename. Loading fails if either is missing.

yolo11m_pose.onnx is an ONNX export of Ultralytics YOLO11m-pose and is licensed under AGPL-3.0. Its corresponding source is available via the open-source BlendCap repository at https://github.com/Arcomade/BlendCap, satisfying the AGPL source-availability requirement. No commercial Ultralytics license is required.

Usage

Loaded automatically by BlendCap when USE_ORT=1 is set. If you're using these directly:

import onnxruntime as ort

session = ort.InferenceSession(
    "backbone_dinov3_fp16.onnx",
    providers=["CUDAExecutionProvider", "DmlExecutionProvider",
               "CoreMLExecutionProvider", "CPUExecutionProvider"],
)

ORT picks the first available execution provider from the list.

Source

• DINOv3 backbone: derived from facebook/sam-3d-body-dinov3 (gated — see Meta's HF for original weights and license acceptance).
• MoGe-2 encoder: derived from Ruicheng/moge-2-vits-normal.
• YOLO11m-pose detector: derived from Ultralytics YOLO11 (AGPL-3.0).
• Exported via the scripts in BlendCap's source repo.