Develop a deep learning model for learning the triangular face label assignment on polycube meshes, ensuring shape fidelity and structural validity requirements are met. -- 2
Budget: $750 – $1,500 USD
This project focuses on label learning tasks based on polycube structures. A polycube is a special geometric structure that aligns with main axes, where each face is perpendicular or parallel to the ±x/±y/±z axes, and adjacent faces are mutually perpendicular.
The input consists of a triangular mesh and its existing label data (indicating the direction of each triangle face as ±x/y/z), and the output is a new label assignment. Existing metric functions are used to evaluate label quality, including:
- Fidelity: The degree of alignment between the label and the face normal.
- Compactness: The smoothness of region boundaries and the number of corner points.
- Validity Conditions: Whether the label combinations can legally form a polycube structure.
We provide:
- 1000+ training data (expandable).
- Label visualization tool (polyscope).
- Validity check function.
- Code for label evaluation metrics.
You need to construct a deep learning model based on the existing data to output high-quality, valid label assignments.
1. Complete Deep Learning CodeInclude training, validation, and prediction sections, capable of reading the existing label data and outputting new mesh labels.
2. Model Design and Performance Evaluation DocumentDocument the framework used, network architecture, loss function design, and training strategies, with model performance on evaluation metrics.
3. Usage Documentation and ExplanationProvide documentation for usage and an explanation of the framework, highlighting key modifications. Support for a Tencent meeting to explain the framework structure and usage (I will record the screen to minimize the frequency of your explanations).
4. Assistance with Writing the PaperHelp organize the technical background and method details of this AI model, such as the network used, why it was designed that way, and comparisons with other methods. It is recommended that you keep a log during development or write a simple development note for my reference.
The input consists of a triangular mesh and its existing label data (indicating the direction of each triangle face as ±x/y/z), and the output is a new label assignment. Existing metric functions are used to evaluate label quality, including:
- Fidelity: The degree of alignment between the label and the face normal.
- Compactness: The smoothness of region boundaries and the number of corner points.
- Validity Conditions: Whether the label combinations can legally form a polycube structure.
We provide:
- 1000+ training data (expandable).
- Label visualization tool (polyscope).
- Validity check function.
- Code for label evaluation metrics.
You need to construct a deep learning model based on the existing data to output high-quality, valid label assignments.
1. Complete Deep Learning CodeInclude training, validation, and prediction sections, capable of reading the existing label data and outputting new mesh labels.
2. Model Design and Performance Evaluation DocumentDocument the framework used, network architecture, loss function design, and training strategies, with model performance on evaluation metrics.
3. Usage Documentation and ExplanationProvide documentation for usage and an explanation of the framework, highlighting key modifications. Support for a Tencent meeting to explain the framework structure and usage (I will record the screen to minimize the frequency of your explanations).
4. Assistance with Writing the PaperHelp organize the technical background and method details of this AI model, such as the network used, why it was designed that way, and comparisons with other methods. It is recommended that you keep a log during development or write a simple development note for my reference.