# arthurdelannoyazerty/mesh-simplification-gnn architecture

> Architecture diagram of the GitHub repository arthurdelannoyazerty/mesh-simplification-gnn, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-01-17). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/arthurdelannoyazerty/mesh-simplification-gnn
- Repository: https://github.com/arthurdelannoyazerty/mesh-simplification-gnn

## Overview

##### Main System Components

a) Data Processing Layer
- 3D model input handling (OBJ/STL files)
- Conversion pipeline (convert_OBJ_to_STL.py)

b) Core Model Architecture
- Point Picker Module
- Triangle Generator Module
- GNN (Graph Neural Network) Components

c) Neural Network Layers
- Various specialized layers (organized hierarchically)
- Model training components

##### Component Relationships

**[3D Model Input] → [Data Processing] → [Point Picker] → [Triangle Generator] → [Mesh Output]**

With detailed sub-components:

**Model Layers:**
- GNN Components
- Convolution Layers
- Attention Mechanisms
- MLP Networks

##### Specific Implementation Details

- Blue: Data input/output components
- Green: Core processing modules
- Yellow: Neural network layers
- Red: Training components

##### Key Architectural Elements to Highlight

a) Model Architecture:
- Point Picker (model_point_picker.py)
- Triangle Generator (model_triangle_generator.py)
- Graph Neural Network components (gnn.py, devconv_gnn.py)

b) Layer Organization:
- Attention mechanisms (sparse_attention_edge_predictor_layer.py)
- Convolution operations (devcon.py)
- Graph operations (knn.py, knn_simple.py)
- Basic neural components (mlp.py, mlp_gnn.py)

c) Training Pipeline:
- Point picker training (train_point_picker.py)
- Triangle generator training (train_triangle_generator.py)
- Loss functions (loss_point_picker.py, loss_triangle_generator.py)

##### Visualization Components
- Visualization modules (viz_model_point_picker_training.py, viz_model_training.py)
- How they interact with the training process

##### Technical Details

Specific technical elements:
- Input formats (OBJ/STL)
- Layer types and connections
- Loss function integration
- Training flow direction
- Visualization feedback mechanisms

## Diagram (Mermaid)

```mermaid
graph TB
    subgraph Data_Processing
        Input[3D Model Input]:::input
        Storage["3D Model Storage"]:::storage
        Converter["File Converter"]:::processor
    end

    subgraph Core_Architecture
        PointPicker["Point Picker Module"]:::core
        TriangleGen["Triangle Generator"]:::core
        
        subgraph GNN_Components
            GNN["GNN Base"]:::nn
            DevConvGNN["DevConv GNN"]:::nn
        end
    end

    subgraph Neural_Layers
        subgraph Attention
            SparseAttention["Sparse Attention Edge Predictor"]:::nn
        end
        
        subgraph Convolution
            DevCon["DevCon Operations"]:::nn
        end
        
        subgraph Basic_Components
            MLP["MLP Networks"]:::nn
            MLPGNN["MLP GNN"]:::nn
            KNN["KNN Operations"]:::nn
            KNNSimple["KNN Simple"]:::nn
        end
    end

    subgraph Training
        PointPickerTrain["Point Picker Training"]:::training
        TriangleGenTrain["Triangle Generator Training"]:::training
        
        subgraph Loss_Functions
            PointPickerLoss["Point Picker Loss"]:::loss
            TriangleGenLoss["Triangle Generator Loss"]:::loss
        end
    end

    subgraph Visualization
        PickerViz["Point Picker Visualization"]:::viz
        TrainingViz["Model Training Visualization"]:::viz
    end

    Dataset["Mesh Dataset"]:::data

    %% Connections
    Input --> Storage
    Storage --> Converter
    Converter --> Dataset
    
    Dataset --> PointPicker
    PointPicker --> TriangleGen
    
    PointPicker --> GNN
    PointPicker --> DevConvGNN
    
    GNN --> SparseAttention
    GNN --> DevCon
    GNN --> MLP
    GNN --> MLPGNN
    GNN --> KNN
    GNN --> KNNSimple
    
    PointPicker --> PointPickerTrain
    TriangleGen --> TriangleGenTrain
    
    PointPickerTrain --> PointPickerLoss
    TriangleGenTrain --> TriangleGenLoss
    
    PointPickerTrain --> PickerViz
    TriangleGenTrain --> TrainingViz

    %% Click Events
    click Storage "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/tree/main/3d_models/"
    click Converter "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/convert_OBJ_to_STL.py"
    click PointPicker "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/model_point_picker.py"
    click TriangleGen "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/model_triangle_generator.py"
    click GNN "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/gnn.py"
    click DevConvGNN "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/devconv_gnn.py"
    click SparseAttention "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/sparse_attention_edge_predictor_layer.py"
    click DevCon "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/devcon.py"
    click MLP "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/mlp.py"
    click MLPGNN "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/mlp_gnn.py"
    click KNN "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/knn.py"
    click KNNSimple "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/layers/knn_simple.py"
    click PointPickerTrain "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/train_point_picker.py"
    click TriangleGenTrain "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/train_triangle_generator.py"
    click PointPickerLoss "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/loss/loss_point_picker.py"
    click TriangleGenLoss "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/loss/loss_triangle_generator.py"
    click PickerViz "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/viz_model_point_picker_training.py"
    click TrainingViz "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/viz_model_training.py"
    click Dataset "https://github.com/ArthurDelannoyazerty/Mesh-simplification-GNN/blob/main/src/model/mesh_dataset.py"

    %% Styles
    classDef input fill:#ADD8E6
    classDef storage fill:#87CEEB
    classDef processor fill:#90EE90
    classDef core fill:#32CD32
    classDef nn fill:#FFD700
    classDef training fill:#FFA07A
    classDef loss fill:#FF6347
    classDef viz fill:#DDA0DD
    classDef data fill:#B0C4DE

    %% Legend
    subgraph Legend
        L1[Input/Output]:::input
        L2[Storage]:::storage
        L3[Processor]:::processor
        L4[Core Components]:::core
        L5[Neural Networks]:::nn
        L6[Training]:::training
        L7[Loss Functions]:::loss
        L8[Visualization]:::viz
        L9[Data Handling]:::data
    end
```
