QtMeshEditor Mesh Segmentation Vegetation Alternatives

QtMeshEditor-mesh-segmentation-building is an open-source ONNX model designed for part segmentation of building meshes in 3D editors. It labels mesh points as wall, roof, window, door, chimney, or foundation, supporting local inference for graphics developers and researchers working with architectural 3D data.

QtMeshEditor Mesh Segmentation Vehicle is a point-cloud part-segmentation model designed to label points within 3D vehicle meshes. Implemented in the style of PointNet++, the model assigns each point in a mesh representing vehicles—such as cars, trucks, planes, or helicopters—to one of several categories: vehicle body, wheel, window, wing, or rotor (propeller). The model is exported in the ONNX format, enabling local inference through ONNX Runtime. This segmentation model is one of several category-specialized models built for use with QtMeshEditor, a free and open-source 3D mesh and animation editor. Within the QtMeshEditor application, a companion point-cloud classifier first detects the mesh category and then dispatches the relevant segmentation model, with this particular model handling vehicle meshes. Related models exist for other categories such as body, vegetation, and building. The model accepts a sampled point cloud as input, specifically in float32 format. QtMeshEditor Mesh Segmentation Vehicle is distributed under the Creative Commons Attribution 4.0 International (cc-by-4.0) license. The aggregate download source for this and related models is referenced as QtMeshEditor-models. The tool is intended for scenarios requiring detailed labeling of 3D vehicle mesh parts, supporting workflows in 3D mesh editing and animation.

QtMeshEditor-facemesh-onnx is an open-source ONNX model for detecting detailed face mesh landmarks in images. It is intended for integration into computer vision pipelines and supports applications like facial morphing and motion capture.

QtMeshEditor-poselandmarks-onnx is an open-source ONNX model for detecting human pose landmarks in images. It is designed for integration into computer vision pipelines, supporting body capture and motion analysis. The model is suitable for developers building pose estimation or motion capture tools.

QtMeshEditor Blazeface is an ONNX-format implementation of Google MediaPipe's BlazeFace short-range face detector. The model is designed to detect faces within images, providing outputs that include bounding box coordinates and six keypoints per anchor. It processes input images of size [1,128,128,3] in RGB format, normalized to the range [-1,1], with aspect ratio preserved through letterboxing using zero borders. The model outputs two primary tensors: regressors, which provide box and keypoint data for each anchor, and classificators, which yield score logits for detected faces. 3. The detected face region of interest, determined from eye keypoints and expanded to a square region, is intended for further processing by a face mesh landmark model. 0 license. The ONNX graph is a direct conversion of the original Google MediaPipe model, including both code and weights under the same license. The conversion process and its numerical parity with the Python MediaPipe reference implementation are documented and verified through provided scripts and documentation. evidence_sufficient": true}

QtMeshEditor-faceblendshapes-onnx is an ONNX model that converts facial images into ARKit-compatible blendshape scores, enabling facial animation and AR applications. It is based on Google MediaPipe's face blendshape model and is suitable for developers building real-time facial tracking or animation tools.

QtMeshEditor-blazepose-onnx is an ONNX model for real-time human pose detection, converted from Google's BlazePose architecture. It allows developers to integrate pose estimation into their applications for research, animation, or fitness tracking purposes.